© 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. 22479
    Prev
    Next
    INDEX
    Explanations

    the word "liquid" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of liquid substances

    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
    reon
    -0.68
    oÄŁ
    -0.65
    ahu
    -0.62
    shire
    -0.62
     Manson
    -0.61
    addon
    -0.60
     Davidson
    -0.60
    alter
    -0.60
    Hur
    -0.59
    CVE
    -0.59
    POSITIVE LOGITS
     nitrogen
    1.18
    ators
    0.96
    itate
    0.86
     electroly
    0.84
     helium
    0.83
     cooled
    0.82
    ation
    0.82
    ileaks
    0.81
     oxygen
    0.81
    ated
    0.80
    Activations Density 0.070%

    No Known Activations