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. 0-RES-JB
    6. 21574
    Prev
    Next
    INDEX
    Explanations

    discussions about various influencing factors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various contributing factors in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clean
    -0.79
    scribe
    -0.78
    ENSE
    -0.70
    DEM
    -0.66
    obook
    -0.65
    arium
    -0.65
    gard
    -0.63
    cious
    -0.63
    boro
    -0.61
     Night
    -0.61
    POSITIVE LOGITS
     factors
    3.66
     Factors
    2.81
     factor
    2.47
     variables
    1.92
     considerations
    1.82
    factor
    1.79
     Factor
    1.67
    Factor
    1.62
     reasons
    1.58
     influences
    1.54
    Activations Density 0.020%

    No Known Activations