© 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. 10130
    Prev
    Next
    INDEX
    Explanations

    references to the concept of a "black box."

    oai_token-act-pair · gpt-3.5-turbo

    references to "black box" concepts or metaphors

    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
    PsyNetMessage
    -0.75
    yip
    -0.67
    ASE
    -0.65
    ALLY
    -0.64
     Lauder
    -0.63
    icular
    -0.63
    ailand
    -0.62
    igslist
    -0.62
    ICLE
    -0.62
    YN
    -0.61
    POSITIVE LOGITS
    smith
    1.48
    listed
    1.31
    ened
    1.23
    berry
    1.12
    jack
    1.10
    berries
    1.08
    hawk
    1.05
    adder
    1.03
    powder
    1.03
    face
    1.02
    Activations Density 0.038%

    No Known Activations