© 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. 11544
    Prev
    Next
    INDEX
    Explanations

    locations or entities with additional contextual details, such as "what is now," "considered," "believed," "viewed," "described," "likely," "considered," and "would be."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the present or past state of being or existence

    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
    ridges
    -0.75
    airs
    -0.72
    ridge
    -0.71
    Footnote
    -0.67
    ience
    -0.61
    carry
    -0.60
    igraph
    -0.59
    toe
    -0.59
    NetMessage
    -0.59
    WHO
    -0.59
    POSITIVE LOGITS
     transpired
    0.70
     approx
    0.69
     termed
    0.68
     presently
    0.67
    rir
    0.66
     Cf
    0.66
     Kard
    0.65
     admittedly
    0.65
     ostensibly
    0.65
    pires
    0.65
    Activations Density 0.094%

    No Known Activations