© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 1046
    Prev
    Next
    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prominently
    -0.63
    emouth
    -0.54
     kneeling
    -0.54
     corresponding
    -0.53
     availability
    -0.52
     ado
    -0.51
     presiding
    -0.51
     Vol
    -0.51
     ardent
    -0.51
     attendance
    -0.50
    POSITIVE LOGITS
    1969
    0.75
     dx
    0.70
    schild
    0.69
    roxy
    0.67
    WARNING
    0.63
    1959
    0.63
    INFO
    0.62
    angler
    0.61
    ancial
    0.61
    1971
    0.61
    Activations Density 0.086%

    No Known Activations