© 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. 11-RES-JB
    11. 23859
    Prev
    Next
    INDEX
    Explanations

    mentions of various names and titles, possibly related to multiple individuals in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "im" or "I" as a personal pronoun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.72
    ttes
    -0.60
     dams
    -0.57
     hyster
    -0.56
     Roh
    -0.56
     Compact
    -0.56
    Ĭ
    -0.55
     amplified
    -0.54
     avoidance
    -0.54
     grease
    -0.54
    POSITIVE LOGITS
    perial
    1.27
    enez
    1.25
    ple
    1.23
    bledon
    1.19
    orph
    1.19
    agine
    1.19
    ultane
    1.18
    etric
    1.13
    izu
    1.11
    pson
    1.11
    Activations Density 0.041%

    No Known Activations