© 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. 14234
    Prev
    Next
    INDEX
    Explanations

    action verbs related to making changes or implementing solutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to potential changes and developments in various contexts

    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
    ogle
    -0.70
     elsewhere
    -0.69
    ........
    -0.69
    ifer
    -0.69
    iak
    -0.68
    Others
    -0.66
    ords
    -0.65
    isode
    -0.65
    ster
    -0.64
    ageddon
    -0.64
    POSITIVE LOGITS
     aesthetics
    0.92
     ability
    0.87
     sizing
    0.84
     swapping
    0.83
     tracking
    0.82
     bathrooms
    0.82
     accessibility
    0.81
     toilets
    0.81
     optimizing
    0.79
     hairst
    0.78
    Activations Density 0.561%

    No Known Activations