© 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. 9-RES-JB
    11. 16211
    Prev
    Next
    INDEX
    Explanations

    technical specifications or product details

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon or creature descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frey
    -0.81
     Kavanaugh
    -0.71
     Zucker
    -0.69
     watered
    -0.66
     Tacoma
    -0.66
     Rudd
    -0.65
     Fox
    -0.65
    hof
    -0.64
     Ford
    -0.64
     Bain
    -0.63
    POSITIVE LOGITS
    eaturing
    1.14
    requency
    1.13
    ategories
    1.07
    ailability
    1.04
    rodu
    1.04
    owered
    1.04
    ounded
    1.03
    autions
    1.01
    anguages
    1.01
    ibliography
    1.00
    Activations Density 0.194%

    No Known Activations