© 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. 8-RES-JB
    11. 6815
    Prev
    Next
    INDEX
    Explanations

    phrases related to prototypes or early versions of products

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prototypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leans
    -0.89
    iris
    -0.82
    die
    -0.81
    relative
    -0.77
    lasses
    -0.76
    scribe
    -0.75
    andra
    -0.72
    olulu
    -0.68
    respond
    -0.68
    otto
    -0.68
    POSITIVE LOGITS
     prototype
    1.06
     prototypes
    1.00
     Prototype
    0.88
     test
    0.86
     testing
    0.85
     sketches
    0.84
     project
    0.79
     phase
    0.79
     mock
    0.78
     stage
    0.78
    Activations Density 0.120%

    No Known Activations