© 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. 10-RES-JB
    11. 24534
    Prev
    Next
    INDEX
    Explanations

    phrases with contrasting elements or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acea
    -0.82
    venge
    -0.72
    inguishable
    -0.71
    escent
    -0.67
    ieth
    -0.66
    aint
    -0.66
    icka
    -0.66
    ĸļ
    -0.65
     ILCS
    -0.65
    edom
    -0.64
    POSITIVE LOGITS
     alas
    1.28
     instead
    1.09
    Instead
    1.04
     postponed
    1.02
     tragically
    0.99
     Instead
    0.96
     opted
    0.96
    failed
    0.92
    instead
    0.91
     failed
    0.90
    Activations Density 0.289%

    No Known Activations