© 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. 2-RES-JB
    11. 12333
    Prev
    Next
    INDEX
    Explanations

    references to someone or something fulfilling the role of a keeper or caretaker

    oai_token-act-pair · gpt-3.5-turbo

    terms related to individuals or roles referred to as 'keepers'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DRAG
    -0.78
    ahime
    -0.75
    NetMessage
    -0.73
    INGS
    -0.72
    çīĪ
    -0.71
     Carbuncle
    -0.67
     elig
    -0.64
    oros
    -0.63
    onson
    -0.62
     REPL
    -0.60
    POSITIVE LOGITS
    keepers
    1.51
    keeper
    1.39
    keeping
    1.33
     keeper
    0.91
    legates
    0.90
    glers
    0.88
    scill
    0.82
    ptin
    0.81
    tale
    0.80
    maid
    0.78
    Activations Density 0.011%

    No Known Activations