© 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. 10041
    Prev
    Next
    INDEX
    Explanations

    phrases related to protests and social issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant societal or cultural issues

    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
     coerc
    -0.56
    ocobo
    -0.55
     comprom
    -0.54
     Vaugh
    -0.52
    retty
    -0.51
     nep
    -0.51
     horizont
    -0.47
    cloth
    -0.46
     anecd
    -0.45
    flix
    -0.45
    POSITIVE LOGITS
    thood
    0.55
    )?
    0.51
     Belfast
    0.51
    anta
    0.49
    obyl
    0.47
    usalem
    0.45
    Ĥİ
    0.44
    '?
    0.44
    ²¾
    0.44
    malink
    0.44
    Activations Density 0.925%

    No Known Activations