© 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. 1747
    Prev
    Next
    INDEX
    Explanations

    words related to consistency or repeated actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "constantly" and its variations, indicating ongoing actions or states

    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
    hemy
    -0.83
    IDA
    -0.75
    rule
    -0.75
    eer
    -0.73
    tein
    -0.68
    AMI
    -0.67
    ERAL
    -0.66
     BDS
    -0.65
    nee
    -0.65
    JV
    -0.64
    POSITIVE LOGITS
     destro
    0.91
     spaced
    0.91
     fluct
    0.89
     constantly
    0.83
    motion
    0.81
     refreshed
    0.81
    ãĥ£
    0.81
     thereafter
    0.81
     evolving
    0.80
     paced
    0.79
    Activations Density 0.011%

    No Known Activations