© 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. 7791
    Prev
    Next
    INDEX
    Explanations

    terms related to data security and technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data collection and utilization

    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
    ĸļ
    -0.84
    idas
    -0.79
    dit
    -0.64
     Mahjong
    -0.64
     Nept
    -0.64
    ovember
    -0.64
    adan
    -0.63
     Canaver
    -0.62
     Vide
    -0.61
    vier
    -0.61
    POSITIVE LOGITS
    secut
    0.56
     antique
    0.54
    quest
    0.54
    under
    0.53
     aerospace
    0.51
     IRC
    0.51
     air
    0.51
    pir
    0.50
    interstitial
    0.50
     ..."
    0.50
    Activations Density 0.139%

    No Known Activations