© 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. 10097
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to being at the center of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating central themes or key concepts within a context

    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
    ishable
    -0.83
    RIP
    -0.75
    pload
    -0.66
    acht
    -0.64
    PASS
    -0.64
    00000
    -0.64
    ----
    -0.62
    hua
    -0.62
    cmp
    -0.61
    à©
    -0.61
    POSITIVE LOGITS
     Blackwell
    0.72
    Initialized
    0.68
     Universities
    0.65
     attracting
    0.65
    gie
    0.64
     convergence
    0.62
     Computing
    0.60
     gravity
    0.59
    obl
    0.59
    aligned
    0.58
    Activations Density 0.096%

    No Known Activations