Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 19204
    Prev
    Next
    INDEX
    Explanations

    phrases where something is being repeated or reiterated

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "echoed" and its variations in the context of repeating sentiments or statements

    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
    aho
    -0.78
    enture
    -0.75
    ahime
    -0.73
    amina
    -0.69
    venge
    -0.69
    ottest
    -0.68
    hibition
    -0.67
    estate
    -0.63
    amins
    -0.63
    uana
    -0.62
    POSITIVE LOGITS
     echoes
    1.20
     echoed
    0.97
     echoing
    0.94
     reverber
    0.87
     voic
    0.81
     reson
    0.80
     chorus
    0.77
    accompan
    0.74
     repeats
    0.73
    choes
    0.73
    Activations Density 0.015%

    No Known Activations