© 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. 6214
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing and programming, like variable names and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    expressions of potential and performance in a sports context

    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
    yna
    -0.69
    uphem
    -0.66
    eva
    -0.66
    aque
    -0.65
    tube
    -0.64
    ricia
    -0.63
    anguage
    -0.61
     Objects
    -0.59
    hiba
    -0.59
     Surve
    -0.58
    POSITIVE LOGITS
     playoff
    1.42
     Playoff
    1.25
     postseason
    1.24
     preseason
    1.18
     offseason
    1.18
     playoffs
    1.17
     offensively
    1.16
     roster
    1.10
     defensively
    1.09
     coaching
    1.08
    Activations Density 1.030%

    No Known Activations