© 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. 2-RES-JB
    11. 20851
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "Anything" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "anything" in various contexts

    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
    ros
    -0.76
    pa
    -0.76
    irth
    -0.72
    seless
    -0.67
    inst
    -0.66
    pas
    -0.63
    steen
    -0.62
    bal
    -0.61
    ffic
    -0.60
    pu
    -0.58
    POSITIVE LOGITS
     else
    1.46
    Else
    1.36
    THING
    1.32
     imaginable
    1.12
     Else
    1.02
     conceivable
    0.94
    else
    0.88
    ĪĴ
    0.85
     remotely
    0.85
     resembling
    0.82
    Activations Density 0.018%

    No Known Activations