© 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. 4-RES-JB
    11. 6082
    Prev
    Next
    INDEX
    Explanations

    terms related to biological implications or explanations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychiatric research and implications

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

    No Comments

    Negative Logits
     Loyal
    -0.74
    Lago
    -0.71
    grim
    -0.68
     Ron
    -0.68
     serv
    -0.68
    vc
    -0.68
     whine
    -0.68
     Chattanooga
    -0.68
    gall
    -0.67
     booted
    -0.67
    POSITIVE LOGITS
     biologically
    1.08
     biomark
    1.03
     âĪ¼
    0.99
     biom
    0.99
     biomedical
    0.99
     hypotheses
    0.98
     overturn
    0.97
     biochemical
    0.96
     epigen
    0.95
     transl
    0.95
    Activations Density 0.231%

    No Known Activations