© 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. 21716
    Prev
    Next
    INDEX
    Explanations

    phrases related to intervention or interference in various situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in."

    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
    catentry
    -0.73
    ŀ
    -0.66
    ãĥĪ
    -0.64
    cia
    -0.64
    lain
    -0.63
    Ŀ
    -0.63
    Ĵ
    -0.62
    ·
    -0.61
    ãĤ¹
    -0.60
    ãĥ«
    -0.58
    POSITIVE LOGITS
    wards
    1.11
     unison
    1.09
    escap
    0.97
    between
    0.96
    ordinate
    0.95
    animate
    0.95
     vitro
    0.94
    humane
    0.92
    bound
    0.92
     front
    0.92
    Activations Density 0.124%

    No Known Activations