© 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. 2-RES-JB
    11. 19388
    Prev
    Next
    INDEX
    Explanations

    texts focusing on different approaches or methods

    oai_token-act-pair · gpt-3.5-turbo

    references to strategies or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.84
    cake
    -0.72
     isot
    -0.69
    arus
    -0.68
    cell
    -0.68
     istg
    -0.68
    ongo
    -0.66
    rd
    -0.64
    circ
    -0.63
     Wak
    -0.62
    POSITIVE LOGITS
     approach
    1.02
     Approach
    0.95
    isons
    0.84
     approaches
    0.82
    ison
    0.81
    yip
    0.79
    heny
    0.75
    idable
    0.74
    IAS
    0.74
    idon
    0.74
    Activations Density 0.015%

    No Known Activations