© 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. 6919
    Prev
    Next
    INDEX
    Explanations

    phrases related to professions serving a specific group or community

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to relationships and community interactions

    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
     Pere
    -0.63
     coincidence
    -0.61
     convergence
    -0.60
     frontal
    -0.60
     Pun
    -0.59
     psychiatrists
    -0.58
     Priest
    -0.57
     spoiler
    -0.57
     Kle
    -0.57
     Ballard
    -0.56
    POSITIVE LOGITS
     dearly
    0.84
    */(
    0.71
    paio
    0.70
    .'
    0.67
    é¾įåĸļ士
    0.67
    ient
    0.66
    )].
    0.66
    .'"
    0.66
    amines
    0.64
    ugen
    0.63
    Activations Density 0.197%

    No Known Activations