© 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. 8135
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the verb "made" in various contexts

    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
    heter
    -0.66
     conditioning
    -0.66
     stripe
    -0.66
    externalActionCode
    -0.66
    TERN
    -0.63
     nurs
    -0.62
    76561
    -0.60
     scrimmage
    -0.60
    assis
    -0.59
     heartbeat
    -0.59
    POSITIVE LOGITS
     sure
    0.91
    ailable
    0.88
     landfall
    0.82
    hift
    0.80
    ÄŁ
    0.79
     headlines
    0.78
    emort
    0.78
    dinand
    0.77
    awaru
    0.77
    netflix
    0.77
    Activations Density 0.120%

    No Known Activations