© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1040
    Prev
    Next
    INDEX
    Explanations

    references or citations indicated by the term "Ref."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or subjects in a discussion

    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
    ciating
    -0.76
    ahime
    -0.72
    daq
    -0.70
     pockets
    -0.66
    ################
    -0.66
    matically
    -0.66
     Horses
    -0.63
     whiff
    -0.63
     atmosphere
    -0.63
     oper
    -0.62
    POSITIVE LOGITS
    eree
    1.47
    lection
    1.39
    lections
    1.39
    riger
    1.33
    erred
    1.27
    erences
    1.25
    lected
    1.25
    lect
    1.23
    erential
    1.23
    eren
    1.22
    Activations Density 0.030%

    No Known Activations