© 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. 8286
    Prev
    Next
    INDEX
    Explanations

    instances where something is being recommended or proposed

    oai_token-act-pair · gpt-3.5-turbo
    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
    bers
    -0.86
    brance
    -0.83
    erning
    -0.81
    vation
    -0.77
    ership
    -0.77
    alde
    -0.77
    tin
    -0.77
    aos
    -0.76
    ctors
    -0.74
    reth
    -0.74
    POSITIVE LOGITS
     suggestions
    0.84
     Parenthood
    0.76
    Attempts
    0.72
     hints
    0.72
     suggested
    0.72
     introdu
    0.71
     unanimously
    0.70
     easing
    0.69
     hint
    0.68
    Magikarp
    0.68
    Activations Density 0.035%

    No Known Activations