© 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. 9-RES-JB
    11. 15719
    Prev
    Next
    INDEX
    Explanations

    locations where violent incidents have occurred

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "in" along with details about various incidents or actions taking place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thous
    -0.81
     importantly
    -0.71
    natureconservancy
    -0.71
    Animation
    -0.71
    issance
    -0.70
    Hist
    -0.67
    soever
    -0.66
     absorbs
    -0.66
    ":"/
    -0.66
     historians
    -0.65
    POSITIVE LOGITS
     retaliation
    1.10
     conjunction
    1.02
     southwestern
    0.98
     southeastern
    0.96
     southwest
    0.94
     Baton
    0.94
    humane
    0.93
     violation
    0.93
     northwestern
    0.92
     lieu
    0.92
    Activations Density 0.239%

    No Known Activations