© 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. 2-RES-JB
    6. 23161
    Prev
    Next
    INDEX
    Explanations

    references to formal organizations or societies

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and societal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     months
    -0.67
    ãĥĦ
    -0.65
    Tube
    -0.64
     vagina
    -0.64
     tubes
    -0.64
    éĹĺ
    -0.63
     Garland
    -0.63
     deliberate
    -0.63
     cunt
    -0.63
     Benghazi
    -0.62
    POSITIVE LOGITS
    ieties
    1.34
    iety
    1.30
    ietal
    1.19
    Soc
    1.18
    isco
    1.12
    soc
    1.07
    ionics
    0.96
     Soc
    0.94
    cer
    0.93
    ocial
    0.90
    Activations Density 0.010%

    No Known Activations