© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 16794
    Prev
    Next
    INDEX
    Explanations

    personal pronouns ('me', 'us', 'them', 'him') indicating individual or collective involvement in actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns that indicate personal involvement or relations

    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
     Amin
    -0.74
     Houses
    -0.72
    town
    -0.68
     Coalition
    -0.66
    otin
    -0.65
     Rory
    -0.64
     Pastebin
    -0.64
     Factory
    -0.62
     Polit
    -0.61
     Onion
    -0.61
    POSITIVE LOGITS
     personally
    0.91
     stride
    0.71
    mie
    0.70
     endeav
    0.70
    é¾įåĸļ士
    0.69
    ãĥķ
    0.69
    ijn
    0.69
     breathing
    0.69
     footing
    0.68
     realise
    0.67
    Activations Density 0.176%

    No Known Activations