© 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. 2-RES-JB
    11. 1382
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Hein" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Hein" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thumbnails
    -0.79
    yip
    -0.73
    tumblr
    -0.71
    âĶģ
    -0.70
    apped
    -0.67
    skirts
    -0.67
    orsi
    -0.64
    ODUCT
    -0.64
    adjusted
    -0.63
    ulet
    -0.63
    POSITIVE LOGITS
     Hein
    1.27
    lein
    1.13
    selage
    0.92
    rich
    0.89
    hardt
    0.86
    zman
    0.81
     Meier
    0.79
     Verb
    0.78
    uve
    0.72
    ischer
    0.72
    Activations Density 0.007%

    No Known Activations