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. 9-RES-JB
    6. 105
    Prev
    Next
    INDEX
    Explanations

    evidence-based information or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate reliance on evidence or data for conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.71
    oward
    -0.68
    ropolis
    -0.68
    odon
    -0.67
    por
    -0.64
    anamo
    -0.64
    scribe
    -0.63
    pload
    -0.62
    ombs
    -0.61
    robe
    -0.61
    POSITIVE LOGITS
     observations
    1.05
     criteria
    0.99
     evaluations
    0.94
     feedback
    0.94
     assumptions
    0.94
     observation
    0.93
    ecd
    0.91
     assumption
    0.90
     intuition
    0.90
     testimonies
    0.87
    Activations Density 0.357%

    No Known Activations