© 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. 3-RES-JB
    11. 8859
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases, particularly those that use commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iple
    -0.79
    ety
    -0.71
    raft
    -0.61
    ishly
    -0.60
    odes
    -0.59
    izon
    -0.57
    ocl
    -0.56
    ¬¼
    -0.56
    uto
    -0.56
    cell
    -0.55
    POSITIVE LOGITS
     namely
    1.09
     albeit
    1.08
     whereas
    0.94
     although
    0.93
     respectively
    0.91
     regardless
    0.84
     lest
    0.84
     thereby
    0.81
     including
    0.79
     culminating
    0.79
    Activations Density 1.425%

    No Known Activations