© 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. 9-RES-JB
    11. 15364
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "pop"

    oai_token-act-pair · gpt-3.5-turbo

    frequent occurrences of the string "pp"

    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
    quished
    -0.78
    pled
    -0.70
    ALLY
    -0.69
    GROUND
    -0.66
     logger
    -0.64
    EStreamFrame
    -0.64
    izons
    -0.61
    MpServer
    -0.61
    USS
    -0.60
    RECT
    -0.59
    POSITIVE LOGITS
    lication
    1.27
    earance
    1.27
    odcast
    1.11
    enhagen
    1.07
    rint
    1.06
    erton
    1.02
    erman
    1.02
    arent
    1.00
    ete
    0.99
    ublic
    0.98
    Activations Density 0.042%

    No Known Activations