© 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. 4-RES-JB
    11. 5108
    Prev
    Next
    INDEX
    Explanations

    references to security and control measures such as curfews, lockdowns, and perimeters

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with boundaries, restrictions, and protective measures

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

    No Comments

    Negative Logits
    union
    -0.80
    gom
    -0.75
    wagen
    -0.74
    gre
    -0.72
    roth
    -0.71
    umo
    -0.70
    ×ķ
    -0.69
    inking
    -0.68
    pec
    -0.67
    ummer
    -0.67
    POSITIVE LOGITS
     lockdown
    1.10
     curfew
    1.07
     perimeter
    0.98
     Authorities
    0.80
     este
    0.79
     patrols
    0.77
     precaution
    0.76
     fence
    0.75
     divid
    0.75
     patrolling
    0.74
    Activations Density 0.010%

    No Known Activations