© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 18457
    Prev
    Next
    INDEX
    Explanations

    large numerical values representing populations or quantities of people

    oai_token-act-pair · gpt-3.5-turbo

    quantitative information related to populations or distances

    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
     parity
    -0.72
     issuer
    -0.66
     Metatron
    -0.66
     Subtle
    -0.64
     Comparison
    -0.64
    Parent
    -0.64
     Digest
    -0.63
     Reality
    -0.63
    ĸļ
    -0.63
    hower
    -0.62
    POSITIVE LOGITS
    km
    1.12
     kilometres
    1.10
     kilometers
    1.09
     hectares
    1.07
     km
    1.02
     miles
    1.01
     metres
    0.96
     acres
    0.93
    sq
    0.89
     hours
    0.87
    Activations Density 0.318%

    No Known Activations