© 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. 1-RES-JB
    11. 23533
    Prev
    Next
    INDEX
    Explanations

    instances of the word "often" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the word "oft" and its variations, indicating commentary on repetition or common occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compatibility
    -0.75
     Disorder
    -0.73
     Handling
    -0.71
     Enhancement
    -0.70
     Formation
    -0.69
     Syndicate
    -0.69
     Flavoring
    -0.66
     Membership
    -0.66
    eering
    -0.65
     UNIVERS
    -0.64
    POSITIVE LOGITS
    entimes
    1.93
     oft
    0.94
     conduc
    0.82
    stress
    0.80
    oit
    0.80
    fort
    0.80
     compr
    0.78
    aez
    0.77
     challeng
    0.77
    ventory
    0.77
    Activations Density 0.003%

    No Known Activations