© 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. 3-RES-JB
    11. 11301
    Prev
    Next
    INDEX
    Explanations

    words related to legal or investigative contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms that indicate connections or associations between different topics or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifter
    -0.79
    IVER
    -0.74
    ARD
    -0.72
     Muller
    -0.70
    UGE
    -0.68
    aneers
    -0.68
    oufl
    -0.67
    \\\\\\\\\\\\\\\\
    -0.67
    ardless
    -0.66
    Bay
    -0.66
    POSITIVE LOGITS
     thereto
    0.92
    ness
    0.83
     reconc
    0.83
     ancest
    0.82
    worldly
    0.82
     newsp
    0.82
     relate
    0.80
     unrelated
    0.76
     related
    0.76
     negatively
    0.75
    Activations Density 0.020%

    No Known Activations