Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19169
    Prev
    Next
    INDEX
    Explanations

    references to the name "Escobar" or words related to the name "Escobar."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Esc" or similar variations in spelling

    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
    fuck
    -0.67
    manship
    -0.67
    cule
    -0.66
     Jenner
    -0.62
     Monthly
    -0.61
     é
    -0.61
     Kos
    -0.61
    ivities
    -0.61
     Dynamics
    -0.61
    gaard
    -0.60
    POSITIVE LOGITS
    apist
    1.39
    ribed
    1.20
    apes
    1.18
    aping
    1.17
    obar
    1.15
    ribing
    1.13
    aped
    1.12
    orts
    1.11
    apers
    1.10
    orting
    1.07
    Activations Density 0.040%

    No Known Activations