© 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. 19789
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities related to companies, locations, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    empty or delimiter tokens that signify the end of text segments

    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
    grass
    -0.73
    falls
    -0.71
    aign
    -0.69
    alli
    -0.68
    lessly
    -0.68
    qv
    -0.66
     Cumm
    -0.66
    liam
    -0.65
    aro
    -0.65
    requ
    -0.65
    POSITIVE LOGITS
    ãĤ¼
    0.73
     {}
    0.72
     Rouge
    0.69
     Azerb
    0.67
    ĵĺ
    0.66
    ש
    0.64
     Universe
    0.61
     Mirage
    0.61
    »Ĵ
    0.61
    ikuman
    0.60
    Activations Density 0.408%

    No Known Activations