© 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. 1-RES-JB
    11. 16821
    Prev
    Next
    INDEX
    Explanations

    terms related to technical details or specifications

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pastry
    -0.82
     veget
    -0.80
     cellar
    -0.74
     chop
    -0.74
     slump
    -0.70
     inund
    -0.70
     dry
    -0.68
     rhy
    -0.68
     pale
    -0.68
     imperson
    -0.68
    POSITIVE LOGITS
    *)
    1.03
    BOOK
    1.01
    aka
    0.97
    ...)
    0.96
    zbollah
    0.94
    saw
    0.93
    insert
    0.89
    https
    0.88
    excluding
    0.88
    ?)
    0.87
    Activations Density 0.068%

    No Known Activations