© 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. 2-RES-JB
    11. 779
    Prev
    Next
    INDEX
    Explanations

    words related to the increase or intensification of actions or events

    oai_token-act-pair · gpt-4-turbo

    terms related to conflict, escalation, and optimization

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conflict, change, and optimization processes

    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
    inal
    -0.76
    ells
    -0.76
    icial
    -0.74
    ¯¯
    -0.71
    otrop
    -0.71
    roc
    -0.70
    estones
    -0.69
    ¯¯¯¯
    -0.69
    encers
    -0.68
    icus
    -0.67
    POSITIVE LOGITS
     prevention
    1.02
     avoidance
    0.94
     lapse
    0.92
     cessation
    0.87
     ende
    0.86
     compulsion
    0.86
    anguage
    0.84
     efforts
    0.83
     initiation
    0.83
     thereof
    0.82
    Activations Density 0.154%

    No Known Activations