© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23471
    Prev
    Next
    INDEX
    Explanations

    web programming terms or technical instructions and specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to logical reasoning and database 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
    اÙĦ
    -0.78
    \\\\\\\\
    -0.77
    Sov
    -0.72
    00007
    -0.70
    ONSORED
    -0.70
    Merit
    -0.69
    çĶ°
    -0.68
    Ö
    -0.68
    âĺ
    -0.66
    issance
    -0.66
    POSITIVE LOGITS
     abound
    0.70
     periphery
    0.65
     interacted
    0.64
     vary
    0.62
     motions
    0.61
     respective
    0.60
     issu
    0.59
     plague
    0.59
     clubs
    0.58
    older
    0.58
    Activations Density 1.072%

    No Known Activations