© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    phrases containing the pattern "one-[number]" where number can be any digit

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing "one-off" events or single instances

    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
     GOODMAN
    -0.72
     Hoo
    -0.69
     Borders
    -0.64
    âĶģ
    -0.62
     Stra
    -0.62
    emetery
    -0.61
    âĸ¬âĸ¬
    -0.60
    ITED
    -0.60
     laun
    -0.58
     SIG
    -0.58
    POSITIVE LOGITS
    sided
    1.38
    dimensional
    1.29
    legged
    1.19
    year
    1.18
    piece
    1.17
    bedroom
    1.14
    handed
    1.13
    minute
    1.13
    eyed
    1.13
    day
    1.07
    Activations Density 0.038%

    No Known Activations