© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 700
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities, such as 'murder', 'convicted', 'serving a life sentence', 'arrested', 'suspected', 'schemes', 'bunker', and names related to individuals involved in crimes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accomplices or associated individuals in a criminal context

    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
    edIn
    -0.87
    Ħ¢
    -0.80
    DEN
    -0.76
    ARB
    -0.72
    acular
    -0.68
    opian
    -0.66
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    Reviewer
    -0.64
    cast
    -0.63
    Ec
    -0.63
    POSITIVE LOGITS
    livion
    0.77
     accompl
    0.72
    pload
    0.72
    illon
    0.69
    vous
    0.67
     kidnap
    0.67
    gang
    0.67
    cart
    0.66
    stration
    0.66
     chorus
    0.66
    Activations Density 0.030%

    No Known Activations