© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of meetings and conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of meetings and gatherings

    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
    less
    -0.60
    \\\\\\\\\\\\\\\\
    -0.59
    lessness
    -0.59
     salvage
    -0.58
    nah
    -0.58
     mosaic
    -0.58
     symbolism
    -0.57
     Problem
    -0.57
     Species
    -0.56
    BUG
    -0.56
    POSITIVE LOGITS
    uggest
    1.35
    hips
    1.31
    chool
    1.19
    hops
    1.15
    poons
    1.12
    hare
    1.06
    hip
    1.05
    hooting
    1.03
    ettings
    1.03
    peak
    1.02
    Activations Density 0.238%

    No Known Activations