© 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. 10-RES-JB
    11. 6938
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    clauses that introduce additional information or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robe
    -0.80
    hoe
    -0.74
    acters
    -0.74
    verts
    -0.74
    amins
    -0.72
    ento
    -0.69
     GEAR
    -0.67
    ESSION
    -0.65
    amps
    -0.65
    ismo
    -0.65
    POSITIVE LOGITS
     albeit
    1.15
     unnamed
    1.05
     lesser
    0.96
     unidentified
    0.95
     simpler
    0.92
     uh
    0.91
     unofficial
    0.90
     unpublished
    0.90
     narrower
    0.90
     unrelated
    0.90
    Activations Density 0.121%

    No Known Activations