© 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. 7-RES-JB
    11. 13404
    Prev
    Next
    INDEX
    Explanations

    words indicating comparison or emphasis, where one thing is more or less than another

    oai_token-act-pair · gpt-3.5-turbo

    frequently used words and phrases that indicate continuity or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Subject
    -0.69
    etting
    -0.64
    Rap
    -0.59
    yond
    -0.59
    onto
    -0.57
    ensing
    -0.57
    Behind
    -0.57
    avier
    -0.55
    acle
    -0.55
     Mats
    -0.54
    POSITIVE LOGITS
    been
    1.50
     been
    1.40
     undergone
    1.22
     become
    1.06
     gotten
    1.04
     begun
    1.01
     gone
    1.01
     fallen
    0.99
     Been
    0.98
     come
    0.96
    Activations Density 0.152%

    No Known Activations