© 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. 8-RES-JB
    11. 18539
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    statements involving the verb "is" along with qualifiers that denote conditions or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pedia
    -0.82
    ERAL
    -0.72
    ths
    -0.71
     Pledge
    -0.69
    Comments
    -0.66
    inav
    -0.64
    itches
    -0.63
     Advice
    -0.62
     Spells
    -0.62
    eva
    -0.61
    POSITIVE LOGITS
     deemed
    1.04
     configured
    1.04
     sufficiently
    1.03
     able
    0.99
     properly
    0.96
    nt
    0.96
     located
    0.95
     not
    0.94
     unavailable
    0.92
     unable
    0.92
    Activations Density 0.208%

    No Known Activations