© 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. 17887
    Prev
    Next
    INDEX
    Explanations

    terms related to rapid or fast-paced actions or developments

    oai_token-act-pair · gpt-3.5-turbo

    references to rapid changes or growth

    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
    obyl
    -0.79
    ______
    -0.78
    mberg
    -0.75
    #$#$
    -0.74
    代
    -0.72
    gdala
    -0.72
    rights
    -0.71
     Helpful
    -0.71
    OULD
    -0.71
    adish
    -0.71
    POSITIVE LOGITS
     succession
    1.14
     turnaround
    0.99
    aneously
    0.98
     paced
    0.98
     influx
    0.91
     outp
    0.84
     pace
    0.84
     transition
    0.83
     transitions
    0.82
     onset
    0.81
    Activations Density 0.006%

    No Known Activations