© 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. 3136
    Prev
    Next
    INDEX
    Explanations

    instances of past tense verbs ending in '-ed'

    oai_token-act-pair · gpt-3.5-turbo

    words related to complex or intricate concepts

    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
    imately
    -0.85
    theless
    -0.83
    ifully
    -0.74
    wise
    -0.70
    cipled
    -0.68
    channelAvailability
    -0.66
    fully
    -0.65
    ificantly
    -0.65
     trained
    -0.63
     silenced
    -0.63
    POSITIVE LOGITS
    stros
    0.93
    unker
    0.91
    otypes
    0.85
    agonist
    0.80
    aution
    0.80
    rawler
    0.79
    izen
    0.79
    eatures
    0.78
    inter
    0.78
    ector
    0.77
    Activations Density 0.343%

    No Known Activations