© 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. 10-RES-JB
    11. 12793
    Prev
    Next
    INDEX
    Explanations

    the phrase 'don't get me', sometimes accompanied by additional words, suggesting a point of view or providing more context

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases that express personal statements or requests for attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roup
    -0.68
    ombs
    -0.66
    ibaba
    -0.64
    ibrary
    -0.64
    SHIP
    -0.64
    ioch
    -0.61
    earable
    -0.61
    pole
    -0.60
    affiliated
    -0.59
    etsk
    -0.58
    POSITIVE LOGITS
    lees
    0.77
    cha
    0.77
    eeee
    0.73
    gyn
    0.73
     sir
    0.72
     thou
    0.71
    elo
    0.71
    adow
    0.70
     dear
    0.68
    zzo
    0.68
    Activations Density 0.046%

    No Known Activations