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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 13717
    Prev
    Next
    INDEX
    Explanations

    phrases expressing familiarity or recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to familiarity or well-known concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ument
    -0.77
    secondary
    -0.76
    ©¶æ
    -0.72
    chnology
    -0.71
    chance
    -0.69
    secution
    -0.68
    ignt
    -0.67
    Ħ¢
    -0.67
    gur
    -0.66
    ĺħ
    -0.65
    POSITIVE LOGITS
    izing
    1.25
    ized
    1.23
    isable
    1.17
    ity
    1.15
    ised
    1.13
    ization
    1.12
    izable
    1.11
    izations
    1.10
    ties
    1.05
    IZ
    1.05
    Activations Density 0.039%

    No Known Activations