© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 839
    Prev
    Next
    INDEX
    Explanations

    significant figures, such as notable individuals, in news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppable
    -0.65
    itters
    -0.63
     Needs
    -0.60
     Admir
    -0.60
    fires
    -0.60
    Interested
    -0.59
     Allow
    -0.58
     bye
    -0.58
    FG
    -0.57
     Carnival
    -0.57
    POSITIVE LOGITS
     been
    1.15
     written
    1.12
     authored
    1.06
     argued
    1.06
     researched
    1.05
     coined
    1.05
     penned
    1.03
     teamed
    1.01
     testified
    0.99
     analysed
    0.96
    Activations Density 0.176%

    No Known Activations