© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19387
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or success

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" and its frequency within various 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
    wine
    -0.72
    casters
    -0.67
    caster
    -0.65
    soever
    -0.64
    ALSE
    -0.63
    INGS
    -0.62
    USB
    -0.61
    NULL
    -0.61
     istg
    -0.61
    dad
    -0.60
    POSITIVE LOGITS
     regards
    1.23
     conjunction
    1.22
    roads
    1.19
     vitro
    1.17
     relation
    1.17
    clus
    1.15
     lieu
    1.11
     spite
    1.11
    clusively
    1.11
     terms
    1.10
    Activations Density 0.287%

    No Known Activations