© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24002
    Prev
    Next
    INDEX
    Explanations

    mentions of ambiguity or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    the word "something" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    de
    -0.69
    assis
    -0.67
    interest
    -0.65
    follow
    -0.64
    DOM
    -0.64
    spread
    -0.63
    lead
    -0.63
    use
    -0.63
    ignore
    -0.62
    bourg
    -0.61
    POSITIVE LOGITS
    Else
    1.30
     else
    1.05
     innocuous
    0.81
     intangible
    0.79
     resembling
    0.79
    ĪĴ
    0.78
     nutritious
    0.77
     incomprehensible
    0.77
     nutrit
    0.76
     tangible
    0.75
    Activations Density 0.036%

    No Known Activations