Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20010
    Prev
    Next
    INDEX
    Explanations

    verbs that describe physical actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to strife or conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.68
    Ô
    -0.67
    eph
    -0.65
    grass
    -0.64
     printing
    -0.64
    STAR
    -0.63
    bill
    -0.61
     Beard
    -0.61
    renheit
    -0.61
    elia
    -0.60
    POSITIVE LOGITS
    ations
    1.12
    uments
    1.12
    aining
    1.12
    ained
    1.07
    ATIONS
    1.06
    icken
    1.06
    antly
    1.05
    ators
    1.01
    ATION
    0.95
    ational
    0.92
    Activations Density 0.043%

    No Known Activations