© 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. 7-RES-JB
    11. 10072
    Prev
    Next
    INDEX
    Explanations

    verbs related to enhancing or modifying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enhancing experiences or qualities

    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
     renamed
    -0.64
     Fundamental
    -0.61
    chnology
    -0.60
     ratified
    -0.60
    iberal
    -0.59
    National
    -0.58
     consulted
    -0.57
    arians
    -0.56
     discredited
    -0.54
     surveyed
    -0.54
    POSITIVE LOGITS
    imum
    0.79
     wearer
    0.75
     equilibrium
    0.68
     texture
    0.68
     pores
    0.66
     versatility
    0.65
     Flavoring
    0.64
     unwanted
    0.64
     edge
    0.62
    llular
    0.62
    Activations Density 0.893%

    No Known Activations