© 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. 8-RES-JB
    11. 3079
    Prev
    Next
    INDEX
    Explanations

    mentions of transactions or exchanges

    oai_token-act-pair · gpt-3.5-turbo

    significant references to actions and decisions made by organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advoc
    -0.64
     compat
    -0.59
    anwhile
    -0.55
     rebell
    -0.55
     charisma
    -0.54
     manif
    -0.53
     experien
    -0.53
     companions
    -0.53
     teammates
    -0.52
    Interstitial
    -0.51
    POSITIVE LOGITS
     its
    0.74
     Its
    0.67
     antitrust
    0.67
     FOIA
    0.66
     Publication
    0.63
     publishing
    0.60
     investigating
    0.58
     releasing
    0.58
     hiring
    0.58
     refund
    0.57
    Activations Density 1.023%

    No Known Activations