© 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. 4010
    Prev
    Next
    INDEX
    Explanations

    words related to decisions, commitments, and stances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to commitments, decisions, and stances on various 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
    ÃŁ
    -0.71
    Jew
    -0.67
    oke
    -0.65
     oneself
    -0.63
    gettable
    -0.60
    racuse
    -0.59
    anton
    -0.59
    hma
    -0.58
    glomer
    -0.58
    ividually
    -0.58
    POSITIVE LOGITS
    lessness
    0.78
    iness
    0.75
     exploits
    0.73
     reliance
    0.73
     foray
    0.72
     towards
    0.72
     woes
    0.70
     abroad
    0.69
    ãĥ¼ãĤ¯
    0.67
    uality
    0.66
    Activations Density 0.321%

    No Known Activations