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

    Neuronpedia

    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. 6-RES-JB
    11. 5198
    Prev
    Next
    INDEX
    Explanations

    mentions of taxi cabs

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    341
    +0.14
    0.7%
    405
    +0.13
    0.7%
    1895
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.14
    0.03
    1971
    +0.13
    0.02
    994
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.62
     intersper
    -0.98
     endow
    -0.88
     quitted
    -0.84
     overcrow
    -0.83
     interposed
    -0.81
     endeavored
    -0.79
     strove
    -0.79
     encomp
    -0.78
     trod
    -0.76
    POSITIVE LOGITS
     Cab
    1.65
     cab
    1.58
    Cab
    1.52
     CAB
    1.30
     cabs
    1.28
    cab
    1.26
    CAB
    1.19
     cabinet
    1.12
     Cabinet
    1.11
    Cabinet
    1.06
    Activations Density 0.304%

    No Known Activations