© 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. 0-RES-JB
    11. 6764
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to directionality, specifically pointing or moving upwards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to upward movement or growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bos
    -0.63
    dll
    -0.62
    INA
    -0.60
    rama
    -0.60
    Phone
    -0.60
    prov
    -0.58
    wolf
    -0.57
    ries
    -0.57
    ne
    -0.57
    BI
    -0.57
    POSITIVE LOGITS
     upwards
    3.56
     upward
    3.01
     downwards
    2.35
     downward
    2.02
     onward
    1.45
     onwards
    1.18
     upt
    1.10
     forwards
    1.01
     uphill
    0.99
     outward
    0.97
    Activations Density 0.016%

    No Known Activations