© 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. 11099
    Prev
    Next
    INDEX
    Explanations

    numbers or lists within brackets

    oai_token-act-pair · gpt-3.5-turbo

    numbers, particularly in a context related to data or instructions

    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
    ãĥ¼ãĥĨ
    -0.59
     ".
    -0.59
     therap
    -0.58
     ",
    -0.58
     âĢİ
    -0.58
     reconc
    -0.57
    alach
    -0.56
     Reneg
    -0.56
     Extras
    -0.55
     airs
    -0.54
    POSITIVE LOGITS
    )
    1.24
    ++)
    0.96
    )(
    0.92
    )'
    0.91
    )"
    0.90
    )=
    0.89
    )...
    0.88
    -)
    0.87
    +)
    0.83
    âĢ¦)
    0.83
    Activations Density 0.073%

    No Known Activations