© 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. 7-RES-JB
    11. 12685
    Prev
    Next
    INDEX
    Explanations

    phrases related to various activities undertaken or initiated by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or quantities associated with measurement or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     describ
    -0.84
     neighb
    -0.83
     oun
    -0.76
     destro
    -0.71
     Mub
    -0.68
     prosec
    -0.66
     Blair
    -0.66
     Sin
    -0.66
     Hero
    -0.66
     Melvin
    -0.65
    POSITIVE LOGITS
    Advertisement
    1.22
    Advertisements
    1.21
    âĨij
    1.20
    RAW
    1.17
    Trivia
    1.17
    ©
    1.13
    Examples
    1.08
    References
    1.08
    Discussion
    1.07
    >>
    1.05
    Activations Density 0.337%

    No Known Activations