© 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. 10-RES-JB
    11. 12797
    Prev
    Next
    INDEX
    Explanations

    statistics and trends in relation to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    crime statistics and rates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dit
    -0.89
     Centauri
    -0.79
    atari
    -0.77
     Emin
    -0.77
     manoeuv
    -0.73
    Tokens
    -0.73
    Stretch
    -0.72
    hai
    -0.72
     Stretch
    -0.71
    raft
    -0.71
    POSITIVE LOGITS
     homicides
    2.16
     homicide
    1.91
     murders
    1.85
     crimes
    1.61
     crime
    1.60
     murder
    1.56
     killings
    1.54
     shootings
    1.53
     robberies
    1.51
    crime
    1.49
    Activations Density 0.489%

    No Known Activations