© 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. 4-RES-JB
    11. 14787
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or behaviors within a story or narrative

    oai_token-act-pair · gpt-3.5-turbo

    punctuated statements or clauses, particularly those indicating disagreement or contrast

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

    No Comments

    Negative Logits
    ¬¼
    -0.71
    UF
    -0.64
    pec
    -0.61
    ety
    -0.60
    orn
    -0.59
    uy
    -0.59
    Accessory
    -0.59
    heast
    -0.59
    lf
    -0.58
    interstitial
    -0.58
    POSITIVE LOGITS
     however
    1.32
     though
    1.23
     albeit
    1.20
     although
    1.12
     huh
    1.03
     but
    1.03
     meanwhile
    0.97
     whereas
    0.94
     namely
    0.92
     insofar
    0.90
    Activations Density 0.939%

    No Known Activations