Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17470
    Prev
    Next
    INDEX
    Explanations

    phrases related to states of mind or mental conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey states of being or existence

    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
    arently
    -0.74
    oother
    -0.73
    eeper
    -0.70
    direct
    -0.69
    arent
    -0.68
     Unsure
    -0.68
     sqor
    -0.66
    ombies
    -0.64
    orous
    -0.64
    untarily
    -0.64
    POSITIVE LOGITS
     sorts
    0.84
     juven
    0.79
     Buddhism
    0.77
     humankind
    0.77
     bip
    0.75
     mankind
    0.74
     feminism
    0.73
     masculinity
    0.72
     theirs
    0.71
     humanity
    0.71
    Activations Density 0.446%

    No Known Activations