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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6597
    Prev
    Next
    INDEX
    Explanations

    instances of words related to degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    the word "slightly" and its variations, indicating slight differences or nuances

    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
    yers
    -0.77
    velt
    -0.75
     Aviv
    -0.74
    iture
    -0.73
    itures
    -0.72
    elsen
    -0.71
    ravings
    -0.70
    uments
    -0.70
    criptions
    -0.68
     Parenthood
    -0.68
    POSITIVE LOGITS
     eccentric
    0.81
     overlap
    0.79
     inconven
    0.79
     overlapping
    0.77
     offset
    0.76
     tang
    0.76
     altered
    0.76
     incl
    0.75
     tilted
    0.74
     inclined
    0.72
    Activations Density 0.030%

    No Known Activations