© 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. 8-RES-JB
    11. 17074
    Prev
    Next
    INDEX
    Explanations

    ideals or idealized concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ideals or idealism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bane
    -0.85
    SEE
    -0.72
    cano
    -0.71
    NetMessage
    -0.66
    books
    -0.65
    cloth
    -0.65
    words
    -0.62
    bars
    -0.62
    ker
    -0.62
    dor
    -0.57
    POSITIVE LOGITS
    istic
    1.46
    istically
    1.39
    ized
    1.24
    ised
    1.13
    ization
    1.10
    izing
    1.04
    imum
    0.99
    ism
    0.98
    istical
    0.98
    izable
    0.97
    Activations Density 0.029%

    No Known Activations