© 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. 2-RES-JB
    11. 24097
    Prev
    Next
    INDEX
    Explanations

    terms related to accusations and syllables

    oai_token-act-pair · gpt-3.5-turbo

    mentions of accusations and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Grant
    -0.93
    render
    -0.75
    Hug
    -0.74
     Grant
    -0.71
    LY
    -0.68
    FactoryReloaded
    -0.67
    IELD
    -0.66
    Donnell
    -0.66
     Protector
    -0.66
     Higgins
    -0.65
    POSITIVE LOGITS
    atory
    0.99
    iaries
    0.97
    ers
    0.94
    atable
    0.91
    estones
    0.84
    atorial
    0.82
    itely
    0.82
    ential
    0.80
    ateur
    0.78
    ļ
    0.78
    Activations Density 0.023%

    No Known Activations