© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    relationships between opposite factors or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    relationships between attributes and their comparative effects

    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
     hadn
    -0.64
    ©¶æ
    -0.62
    recent
    -0.61
    bare
    -0.60
     somew
    -0.60
    empl
    -0.59
    irez
    -0.59
    esides
    -0.58
    albeit
    -0.58
    asa
    -0.57
    POSITIVE LOGITS
     becomes
    0.99
     chances
    0.83
     chance
    0.79
     decreases
    0.79
    rier
    0.76
     become
    0.73
     tendency
    0.73
     tends
    0.73
     likelihood
    0.71
     temptation
    0.71
    Activations Density 0.191%

    No Known Activations