© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6838
    Prev
    Next
    INDEX
    Explanations

    phrases related to curves and slopes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to curved shapes and slopes

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

    No Comments

    Negative Logits
     Wond
    -0.80
    acl
    -0.70
    alogue
    -0.67
    Veter
    -0.67
    achu
    -0.67
    agi
    -0.66
    ota
    -0.65
    ocus
    -0.64
    phan
    -0.64
    ulet
    -0.64
    POSITIVE LOGITS
     slope
    1.06
     slopes
    1.02
     curv
    0.96
     curves
    0.94
     bends
    0.93
     flatt
    0.91
     curved
    0.91
     valleys
    0.87
     stripes
    0.85
     angles
    0.85
    Activations Density 0.052%

    No Known Activations