© 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. 3-RES-JB
    11. 8367
    Prev
    Next
    INDEX
    Explanations

    keywords for software development such as "Script" and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to scripts or scriptwriting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RSS
    -0.71
     parasite
    -0.64
     ADS
    -0.64
     parasites
    -0.61
     circulation
    -0.61
    izoph
    -0.60
     Constantine
    -0.59
     millenn
    -0.59
     Nicaragua
    -0.59
     light
    -0.58
    POSITIVE LOGITS
    cks
    0.82
    limits
    0.75
    Je
    0.75
    XL
    0.69
    teness
    0.69
    ortment
    0.66
    uns
    0.66
    agu
    0.64
    Shape
    0.63
    rolled
    0.63
    Activations Density 0.000%

    No Known Activations