Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6249
    Prev
    Next
    INDEX
    Explanations

    phrases related to radical ideas or movements

    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
    161
    +0.25
    1.3%
    871
    +0.21
    1.1%
    82
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.25
    0.04
    871
    +0.21
    0.03
    1351
    +0.18
    0.03
    Negative Logits
    <bos>
    -1.19
    deposit
    -0.60
    Pey
    -0.60
    Trabaj
    -0.59
     deposit
    -0.59
    EnumMember
    -0.58
    눠
    -0.58
    Fonto
    -0.58
    Abbiamo
    -0.57
    htbp
    -0.56
    POSITIVE LOGITS
     Radical
    1.44
    Radical
    1.33
    radical
    1.29
     radical
    1.26
     gaily
    1.25
     laft
    1.18
     yves
    1.14
     ftu
    1.14
     frankfurt
    1.13
     leaft
    1.13
    Activations Density 0.393%

    No Known Activations