Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21484
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating absence, negation, or futility

    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
    ahime
    -0.84
     [|
    -0.73
    majority
    -0.61
    lance
    -0.60
     sometime
    -0.58
    gart
    -0.58
    ghan
    -0.57
    asus
    -0.57
    olds
    -0.57
     AX
    -0.56
    POSITIVE LOGITS
    except
    1.03
     whatsoever
    1.01
     except
    0.98
     resembling
    0.83
     besides
    0.76
     nor
    0.73
    imilar
    0.72
    Except
    0.71
    ificant
    0.70
    ensical
    0.69
    Activations Density 0.172%

    No Known Activations