© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 344
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a passage of time or a delay in action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1872
    +0.09
    0.3%
    1323
    +0.08
    0.2%
    1604
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.09
    0.04
    1363
    +0.08
    0.03
    1343
    +0.08
    0.03
    Negative Logits
    ButtonModule
    -0.67
    paddingVertical
    -0.65
    marginHorizontal
    -0.64
    }]
    -0.60
    MatButtonModule
    -0.59
    DeleteMapping
    -0.59
    PutMapping
    -0.58
    alignSelf
    -0.57
    ba
    -0.57
    endl
    -0.57
    POSITIVE LOGITS
     awhile
    1.81
     affor
    1.55
     unden
    1.53
     fortn
    1.48
     viciss
    1.42
     indestru
    1.42
     philanth
    1.40
     stockholm
    1.39
     wherea
    1.39
     hoody
    1.37
    Activations Density 0.306%

    No Known Activations