© 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. 7-RES-JB
    11. 23409
    Prev
    Next
    INDEX
    Explanations

    phrases related to influencing or changing processes or systems

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to processes and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    voy
    -0.63
    cffffcc
    -0.63
     Boat
    -0.61
    sonian
    -0.60
    chest
    -0.59
    brew
    -0.59
    herry
    -0.57
     blot
    -0.56
    oids
    -0.56
    cession
    -0.56
    POSITIVE LOGITS
     interact
    0.76
     Different
    0.73
     interacts
    0.71
     regard
    0.68
     interacting
    0.67
    Different
    0.66
     shaping
    0.66
     structured
    0.64
    ecycle
    0.64
     efficiently
    0.64
    Activations Density 0.356%

    No Known Activations