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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 1328
    Prev
    Next
    INDEX
    Explanations

    instances of the word "somewhat" within the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a level of uncertainty or moderate evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abad
    -0.85
    ocaust
    -0.79
    ULTS
    -0.77
    ults
    -0.76
     Delivery
    -0.74
    elsen
    -0.72
    yrs
    -0.71
    ordan
    -0.71
    rights
    -0.71
    eret
    -0.70
    POSITIVE LOGITS
     amusing
    0.91
     resembling
    0.85
     surprising
    0.85
     confusing
    0.85
     independ
    0.83
     obscure
    0.83
     analogous
    0.82
     reminiscent
    0.82
     cryptic
    0.81
     ironic
    0.81
    Activations Density 0.024%

    No Known Activations