© 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. 4-RES-JB
    11. 13124
    Prev
    Next
    INDEX
    Explanations

    terms related to speed or quickness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rapid" indicating a fast pace or speed in various contexts

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

    No Comments

    Negative Logits
    #$#$
    -0.80
     ç¥ŀ
    -0.76
    roma
    -0.75
    gdala
    -0.73
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.71
     Sins
    -0.69
    代
    -0.68
    mberg
    -0.68
    yer
    -0.67
     Borders
    -0.67
    POSITIVE LOGITS
     succession
    1.00
    aneously
    1.00
     paced
    0.97
     turnaround
    0.94
     prototyp
    0.84
     influx
    0.83
     outp
    0.81
     transit
    0.80
    ity
    0.80
     ascent
    0.79
    Activations Density 0.010%

    No Known Activations