© 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. 1-RES-JB
    11. 10462
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishing something or laying down a foundation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "establish."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bron
    -0.71
    Jac
    -0.67
    har
    -0.65
     Slate
    -0.64
    Crystal
    -0.63
    hop
    -0.61
    cious
    -0.61
    han
    -0.60
     sorry
    -0.60
    andro
    -0.59
    POSITIVE LOGITS
    ablish
    1.16
     establishes
    1.02
    lishes
    0.98
    ablished
    0.96
     establish
    0.93
     mosqu
    0.82
    ablishment
    0.81
     estab
    0.81
    querque
    0.80
    established
    0.80
    Activations Density 0.009%

    No Known Activations