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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 2384
    Prev
    Next
    INDEX
    Explanations

    statistical or factual information

    oai_token-act-pair · gpt-3.5-turbo

    recurring references to factual statements or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.83
     Klux
    -0.81
    artney
    -0.75
    isoft
    -0.72
    JV
    -0.71
    jri
    -0.69
     Carbuncle
    -0.68
    gewater
    -0.68
     charcoal
    -0.67
    hod
    -0.67
    POSITIVE LOGITS
    ually
    1.29
    orial
    1.18
    ional
    1.15
    itious
    1.08
    oids
    1.03
    ual
    1.02
    ially
    0.95
    oid
    0.95
    uality
    0.91
    icity
    0.89
    Activations Density 0.028%

    No Known Activations