© 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. 0-RES-JB
    11. 22432
    Prev
    Next
    INDEX
    Explanations

    assertive statements asserting information or ownership

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "claim."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izontal
    -0.74
    cens
    -0.66
    icult
    -0.65
     Enh
    -0.64
    girls
    -0.64
    orks
    -0.62
     Oo
    -0.61
    uts
    -0.61
    sticks
    -0.60
    allo
    -0.60
    POSITIVE LOGITS
     claim
    3.67
     claims
    2.39
     Claim
    2.36
    Claim
    2.21
     claimed
    2.06
    claim
    1.90
     Claims
    1.88
     assertion
    1.78
     allegation
    1.77
     claiming
    1.73
    Activations Density 0.014%

    No Known Activations