© 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. 24384
    Prev
    Next
    INDEX
    Explanations

    descriptions of achievements or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of media, events, or activities

    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
    Recomm
    -0.76
    Ire
    -0.73
    ×ŀ
    -0.71
    âĸ¬
    -0.71
    igr
    -0.71
    Arg
    -0.66
    ãĥį
    -0.65
    Witness
    -0.63
    omever
    -0.61
    Benz
    -0.59
    POSITIVE LOGITS
     abound
    1.40
     are
    1.23
     aren
    1.14
    heet
    1.06
     await
    1.05
     emerge
    1.04
    etting
    1.02
     were
    1.01
     collide
    0.99
     ARE
    0.99
    Activations Density 0.460%

    No Known Activations