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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 21993
    Prev
    Next
    INDEX
    Explanations

    pronouns representing people or entities

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly "they" and "it," indicating a focus on subjects and their relationships in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eleven
    -0.70
    âĢ¢âĢ¢
    -0.70
    scription
    -0.68
    wikipedia
    -0.68
    Iowa
    -0.67
    thood
    -0.66
    Anne
    -0.65
     Tyr
    -0.65
    Ni
    -0.64
    Dis
    -0.63
    POSITIVE LOGITS
     lacked
    0.85
     dared
    0.84
     lacks
    0.79
     tremend
    0.77
     knew
    0.76
     didn
    0.76
    uristic
    0.76
     messed
    0.76
     cumbers
    0.75
     got
    0.74
    Activations Density 0.173%

    No Known Activations