© 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. 7-RES-JB
    11. 18344
    Prev
    Next
    INDEX
    Explanations

    descriptions of comparisons or contrasts between different elements

    oai_token-act-pair · gpt-3.5-turbo

    complex relationships or comparisons between quantitative variables or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hesitated
    -0.63
     resembled
    -0.62
     reminded
    -0.61
     tripled
    -0.60
     dodged
    -0.60
     apologized
    -0.60
     echoed
    -0.60
     thanked
    -0.59
     lied
    -0.58
     glanced
    -0.58
    POSITIVE LOGITS
     counterparts
    0.80
     ones
    0.72
     realities
    0.72
     counterpart
    0.68
     Telesc
    0.65
    existing
    0.64
     incumbent
    0.63
     extremes
    0.63
    illon
    0.62
    orable
    0.62
    Activations Density 0.652%

    No Known Activations