© 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. 9-RES-JB
    11. 18647
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" followed by a variety of different terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edom
    -0.70
    indal
    -0.69
    anooga
    -0.69
    estyle
    -0.68
    kefeller
    -0.65
    estyles
    -0.64
    Published
    -0.63
    orum
    -0.63
    idium
    -0.63
    istries
    -0.62
    POSITIVE LOGITS
    lihood
    1.09
     previous
    0.84
     many
    0.80
     other
    0.72
     predecessors
    0.71
     any
    0.70
     elsewhere
    0.70
     countless
    0.68
     all
    0.66
     usual
    0.66
    Activations Density 0.105%

    No Known Activations