© 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. 20206
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to form or format

    oai_token-act-pair · gpt-3.5-turbo

    variations and instances of the term "form" across different contexts

    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
     railing
    -0.66
     Hots
    -0.62
    âĶĢâĶĢ
    -0.60
    >>\
    -0.60
     VIDEOS
    -0.60
    selves
    -0.60
     Silence
    -0.59
    visor
    -0.59
    sung
    -0.59
     spot
    -0.58
    POSITIVE LOGITS
    aldehyde
    1.51
    idable
    1.29
    atted
    1.23
    atter
    1.21
    ulas
    1.17
    ulating
    1.13
    ula
    1.11
    ative
    1.10
    ulator
    1.07
    ulates
    1.05
    Activations Density 0.033%

    No Known Activations