© 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. 8-RES-JB
    11. 3097
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events that involve a significant change or impact

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles associated with actions and processes

    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
    igmatic
    -0.76
    inately
    -0.69
    eva
    -0.67
    ordon
    -0.67
    mented
    -0.66
    uate
    -0.65
     Somers
    -0.63
    ounty
    -0.62
    inct
    -0.62
    redo
    -0.61
    POSITIVE LOGITS
    redients
    1.07
     spree
    1.07
    tons
    0.99
     ability
    0.91
    rights
    0.91
     prowess
    0.83
     frenzy
    0.82
     mechanism
    0.82
     motions
    0.80
     techniques
    0.79
    Activations Density 0.431%

    No Known Activations