© 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. 3303
    Prev
    Next
    INDEX
    Explanations

    information related to people's relationships and interactions, such as reunions, family members, and suspicious behavior

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain unique identifiers or distinct categories without any other content

    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
    ogl
    -0.56
    Requ
    -0.56
     increment
    -0.55
     implementations
    -0.55
     broader
    -0.54
    Flow
    -0.53
     Infrastructure
    -0.53
    Configuration
    -0.53
    efficiency
    -0.53
    ERO
    -0.53
    POSITIVE LOGITS
     raped
    0.88
     abducted
    0.78
     died
    0.76
     daughter
    0.76
     kidnapped
    0.75
     sentenced
    0.75
     murdered
    0.74
     stabbed
    0.73
     rapist
    0.73
     survived
    0.72
    Activations Density 0.550%

    No Known Activations