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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14565
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a strong emphasis or conclude statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pretended
    -0.76
     default
    -0.72
     gamb
    -0.69
     defaults
    -0.69
     split
    -0.68
     pse
    -0.68
     splits
    -0.68
     misdem
    -0.66
    iliated
    -0.66
    cheat
    -0.66
    POSITIVE LOGITS
     Moreover
    1.22
    <|endoftext|>
    1.20
     Additionally
    1.16
     Furthermore
    1.16
     However
    1.13
     Nevertheless
    1.12
     Indeed
    1.08
     Unfortunately
    1.08
     Accordingly
    1.07
     Nonetheless
    1.06
    Activations Density 0.547%

    No Known Activations