© 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. 10-RES-JB
    11. 14062
    Prev
    Next
    INDEX
    Explanations

    actions or tasks outlined in a step-by-step format

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or steps to achieve certain goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +.
    -0.69
    .''.
    -0.64
    usercontent
    -0.59
     Travels
    -0.58
    .�
    -0.58
    signed
    -0.58
    .''
    -0.57
    ãģ®å
    -0.57
    !.
    -0.56
    perty
    -0.55
    POSITIVE LOGITS
     properly
    0.77
     further
    0.76
     fullest
    0.69
    uate
    0.69
     truly
    0.68
     purposes
    0.65
     deeper
    0.63
     analogy
    0.62
     this
    0.60
    erning
    0.60
    Activations Density 0.188%

    No Known Activations