© 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. 4-RES-JB
    11. 10193
    Prev
    Next
    INDEX
    Explanations

    phrases indicating past experiences or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "had" in various contexts

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

    No Comments

    Negative Logits
     smokes
    -0.59
    Soc
    -0.59
    Domain
    -0.58
     /**
    -0.57
    #$
    -0.57
     Sta
    -0.57
    Gameplay
    -0.56
     salute
    -0.56
     backdrop
    -0.55
    Products
    -0.55
    POSITIVE LOGITS
     undergone
    1.10
     been
    1.02
     gotten
    0.93
     gone
    0.90
    been
    0.88
    ĸļ
    0.88
    iths
    0.84
     dealings
    0.83
     seen
    0.83
    rontal
    0.80
    Activations Density 0.062%

    No Known Activations