© 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. 8-RES-JB
    11. 6374
    Prev
    Next
    INDEX
    Explanations

    instructions or descriptions that establish a sequence of actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating procedures or instructions, especially those that include the phrase "as follows."

    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
    cest
    -0.63
    Us
    -0.62
    ubb
    -0.60
    minist
    -0.59
    press
    -0.58
    ILA
    -0.57
    ricular
    -0.56
    answered
    -0.55
    ulous
    -0.55
     wonders
    -0.54
    POSITIVE LOGITS
    :"
    1.03
    :-
    1.00
    :
    1.00
    :[
    0.97
     ):
    0.84
    :(
    0.82
    :]
    0.82
    ":
    0.80
    :'
    0.79
    >:
    0.79
    Activations Density 0.057%

    No Known Activations