© 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. 10102
    Prev
    Next
    INDEX
    Explanations

    the phrase "at one point" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at one point."

    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
     vib
    -0.67
    velop
    -0.66
     twins
    -0.59
     cyt
    -0.58
    ente
    -0.58
     hearts
    -0.58
    @#&
    -0.57
    soType
    -0.57
     blues
    -0.57
     quint
    -0.56
    POSITIVE LOGITS
    upon
    0.74
    Footnote
    0.72
    assian
    0.71
    anooga
    0.68
    itia
    0.68
    manship
    0.66
    £ı
    0.66
    ulk
    0.66
     climax
    0.65
    acle
    0.65
    Activations Density 0.029%

    No Known Activations