© 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. 20192
    Prev
    Next
    INDEX
    Explanations

    phrases related to instruction or guidance, particularly in a technical or instructive context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of large numbers or significant references in a document

    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
     estranged
    -0.82
     antit
    -0.76
    apon
    -0.71
    ennes
    -0.71
     manoeuv
    -0.68
     dissu
    -0.68
    heit
    -0.67
     inadequate
    -0.67
     ideal
    -0.66
    rad
    -0.65
    POSITIVE LOGITS
    Anyway
    1.38
     Anyway
    1.29
    ³³³
    1.15
    ³³³³³³³³³³³³³³³³
    1.05
    ³³
    1.03
    ↵Âł
    0.99
    ³³³³
    0.97
    UPDATE
    0.93
    Also
    0.89
    EDIT
    0.88
    Activations Density 0.507%

    No Known Activations