© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 15312
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the absence of doubt or ambiguity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express absolute certainty or lack of doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seless
    -0.93
    spect
    -0.81
    using
    -0.73
    raz
    -0.70
    pat
    -0.69
    grid
    -0.68
    ÅĤ
    -0.68
    fil
    -0.68
    ku
    -0.67
    bern
    -0.67
    POSITIVE LOGITS
     whatsoever
    0.99
    soever
    0.96
    THING
    0.89
     else
    0.87
     except
    0.87
     resembling
    0.86
     ensued
    0.80
     existed
    0.80
     happened
    0.80
     transpired
    0.80
    Activations Density 0.021%

    No Known Activations