© 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. 7998
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refer" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    words related to referencing or citation

    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
     whiff
    -0.67
    urity
    -0.63
    alach
    -0.63
     anch
    -0.57
    é¾įå
    -0.57
     inhib
    -0.56
    cape
    -0.56
     resistance
    -0.55
    ilings
    -0.55
     retaining
    -0.55
    POSITIVE LOGITS
    entious
    1.00
    irect
    1.00
    itatively
    0.90
    minist
    0.86
    rers
    0.81
    entials
    0.76
    rences
    0.76
    ename
    0.75
    ãĥĥ
    0.74
    erential
    0.73
    Activations Density 0.035%

    No Known Activations