© 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. 9866
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names with the pattern "ain"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ain" in various contexts

    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
    ILY
    -0.69
     Cosponsors
    -0.60
     externalToEVAOnly
    -0.59
     mitigating
    -0.57
    kefeller
    -0.57
     SAP
    -0.56
    HAEL
    -0.56
     HELP
    -0.56
    ORK
    -0.55
    ENDED
    -0.55
    POSITIVE LOGITS
    thood
    1.26
    esville
    1.17
    fo
    1.14
    tenance
    1.13
    wright
    1.10
    bow
    1.09
    es
    1.01
    ese
    1.00
    iae
    0.95
    ty
    0.93
    Activations Density 0.040%

    No Known Activations