© 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. 10-RES-JB
    11. 6305
    Prev
    Next
    INDEX
    Explanations

    words related to essential qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of essence or essentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.86
    vernment
    -0.77
    KEN
    -0.73
    MSN
    -0.67
     vitro
    -0.65
    bing
    -0.65
    Äĩ
    -0.63
    webkit
    -0.63
    zing
    -0.59
    ASED
    -0.58
    POSITIVE LOGITS
    entially
    1.42
    entials
    1.40
    enger
    1.25
    andro
    1.18
    ence
    1.07
    ential
    1.06
    ources
    1.00
    omething
    0.98
    ively
    0.96
    ives
    0.94
    Activations Density 0.034%

    No Known Activations