© 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. 6-RES-JB
    11. 14149
    Prev
    Next
    INDEX
    Explanations

    phrases introducing a given statement or context

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Given" indicating a presentation of information or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jer
    -0.86
    ater
    -0.80
    imming
    -0.75
    oiler
    -0.75
    adr
    -0.73
    Bay
    -0.73
    uttering
    -0.69
    aird
    -0.69
    taboola
    -0.68
    ${
    -0.67
    POSITIVE LOGITS
    rely
    0.82
    imaru
    0.81
    stellar
    0.67
     hindsight
    0.63
    cknowled
    0.60
     incapac
    0.60
    intendent
    0.60
    ©¶æ
    0.60
     McF
    0.59
    oko
    0.58
    Activations Density 0.035%

    No Known Activations