© 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. 10-RES-JB
    11. 24360
    Prev
    Next
    INDEX
    Explanations

    references to various camps and locations, potentially related to military or recreational activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Camp" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.90
     regress
    -0.68
     accelerator
    -0.67
    liness
    -0.63
     text
    -0.60
     wording
    -0.60
     otherwise
    -0.59
     knot
    -0.58
     language
    -0.58
     foll
    -0.58
    POSITIVE LOGITS
    agna
    1.17
    bell
    1.15
    agne
    1.11
    aign
    1.04
    ground
    1.02
    agn
    1.01
    sites
    1.00
    fires
    0.99
    sie
    0.98
    ione
    0.96
    Activations Density 0.021%

    No Known Activations