© 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. 1-RES-JB
    11. 11342
    Prev
    Next
    INDEX
    Explanations

    mathematical and financial terms related to differences or variations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to differentiation and distinctions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UG
    -0.85
    à¥
    -0.81
    fulness
    -0.79
    FUL
    -0.77
    000
    -0.75
    igs
    -0.73
    adows
    -0.72
    EF
    -0.72
    ful
    -0.71
    uble
    -0.71
    POSITIVE LOGITS
     differential
    1.31
    iple
    1.17
     hemor
    1.01
    eatures
    0.96
     equations
    0.92
    wcs
    0.90
     allocation
    0.87
    yip
    0.86
     calculus
    0.84
    intendent
    0.83
    Activations Density 0.016%

    No Known Activations