© 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. 9365
    Prev
    Next
    INDEX
    Explanations

    the concept of something being physically on or physically carried by something else

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes of integration or inclusion

    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
    QB
    -0.72
    _-
    -0.72
    rough
    -0.71
    adr
    -0.70
    720
    -0.69
    othy
    -0.69
    FORE
    -0.69
     Hague
    -0.69
    MER
    -0.68
    FE
    -0.67
    POSITIVE LOGITS
     onboard
    1.05
    etooth
    0.83
     impulse
    0.80
    unci
    0.79
    ĨĴ
    0.76
    ments
    0.74
     boarding
    0.74
    ĵĺ
    0.74
    htaking
    0.73
     instinct
    0.72
    Activations Density 0.005%

    No Known Activations