© 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. 7-RES-JB
    11. 18091
    Prev
    Next
    INDEX
    Explanations

    keywords related to various objects and concepts that can be associated with physical structures or hierarchies

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with structure, organization, and safety in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rencies
    -0.83
    urches
    -0.79
    ernels
    -0.79
    iences
    -0.75
     trophies
    -0.75
    atives
    -0.75
    tons
    -0.75
    itudes
    -0.71
    sites
    -0.71
    Ps
    -0.71
    POSITIVE LOGITS
     cutter
    0.79
    hole
    0.78
    igmatic
    0.77
     nucleus
    0.77
    less
    0.77
    ogram
    0.76
    walker
    0.76
     breaker
    0.75
    ribe
    0.74
    alyst
    0.74
    Activations Density 0.500%

    No Known Activations