© 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. 8-RES-JB
    11. 6461
    Prev
    Next
    INDEX
    Explanations

    locations where violent events occur, especially involving crimes or attacks

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating locations or contexts of incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inval
    -0.84
     thous
    -0.79
    issance
    -0.77
     absorbs
    -0.72
     physicists
    -0.67
    âĿ
    -0.67
     engineers
    -0.67
     incumb
    -0.67
    }}}
    -0.66
     importantly
    -0.64
    POSITIVE LOGITS
     lieu
    1.16
     conjunction
    1.15
     retaliation
    1.03
     southwestern
    1.01
     accordance
    0.99
     downtown
    0.98
     relation
    0.96
     southeastern
    0.95
    jured
    0.94
    efficiency
    0.93
    Activations Density 0.263%

    No Known Activations