© 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. 4-RES-JB
    11. 435
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to margins or errors

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical margins of error

    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
    wagen
    -0.76
     Machina
    -0.65
    ergy
    -0.65
     Uz
    -0.64
    JECT
    -0.62
    tics
    -0.62
    iring
    -0.60
    Rod
    -0.59
    ridge
    -0.59
     Chak
    -0.59
    POSITIVE LOGITS
     margin
    1.20
     margins
    0.91
    asonic
    0.78
    margin
    0.77
    oshenko
    0.74
     landslide
    0.74
     difference
    0.74
     separating
    0.73
    olicy
    0.71
    ideon
    0.70
    Activations Density 0.007%

    No Known Activations