© 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. 6-RES-JB
    11. 7607
    Prev
    Next
    INDEX
    Explanations

    digital identifiers such as usernames or version numbers in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    identifiers related to games or gaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.67
     crossings
    -0.65
     footing
    -0.65
     intersections
    -0.64
     passage
    -0.61
    illions
    -0.60
    ecause
    -0.60
     reciproc
    -0.59
    luster
    -0.59
    Jane
    -0.58
    POSITIVE LOGITS
     alias
    0.75
    gmail
    0.73
    nl
    0.71
     Telegram
    0.71
    Script
    0.70
    vous
    0.69
     Profile
    0.67
     Joined
    0.67
    Plugin
    0.67
     Ubuntu
    0.66
    Activations Density 0.305%

    No Known Activations