© 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. 20035
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific or laboratory experiments

    oai_token-act-pair · gpt-3.5-turbo

    punctuated statements or sentences summarizing scientific concepts

    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
    icent
    -0.79
     comfort
    -0.76
     holiday
    -0.76
     affili
    -0.73
     advis
    -0.73
     hug
    -0.72
     peace
    -0.70
     sob
    -0.69
     grade
    -0.68
    enged
    -0.67
    POSITIVE LOGITS
     Eventually
    1.16
     Essentially
    1.15
     Consequently
    1.11
     Each
    1.09
     These
    1.06
     Additionally
    1.05
     Unlike
    1.04
     Using
    1.02
     Depending
    1.02
     Normally
    1.01
    Activations Density 0.408%

    No Known Activations