© 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. 2056
    Prev
    Next
    INDEX
    Explanations

    the desire for something specific to happen or be a certain way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "be" and its variations in different contexts

    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
    PsyNetMessage
    -0.70
     sqor
    -0.68
     convol
    -0.67
     Prescott
    -0.65
     Lines
    -0.63
     srfAttach
    -0.62
     Borders
    -0.61
     Dragonbound
    -0.61
     slope
    -0.60
     fray
    -0.60
    POSITIVE LOGITS
    leeve
    0.98
    arers
    0.97
     able
    0.85
    hemoth
    0.81
    acons
    0.80
    agnetic
    0.80
    ijing
    0.79
    ige
    0.77
     healed
    0.74
     taken
    0.73
    Activations Density 0.128%

    No Known Activations