© 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. 6-RES-JB
    11. 6434
    Prev
    Next
    INDEX
    Explanations

    phrases related to internet scams and hoaxes

    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
    966
    +0.14
    0.8%
    699
    +0.12
    0.7%
    1101
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.14
    0.04
    966
    +0.12
    0.03
    144
    +0.11
    0.03
    Negative Logits
    <bos>
    -1.91
     dobbiamo
    -0.71
    Ngoài
    -0.68
     stiamo
    -0.67
     succede
    -0.67
    ContentAlignment
    -0.61
     facciamo
    -0.61
    bibnamefont
    -0.60
     voglio
    -0.60
    Chúng
    -0.59
    POSITIVE LOGITS
     Ho
    1.31
     maneu
    1.26
     indestru
    1.22
    Ho
    1.20
     héro
    1.19
     renfer
    1.16
     prétend
    1.12
     hcm
    1.11
     confé
    1.11
     disreg
    1.11
    Activations Density 0.244%

    No Known Activations