© 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. 4-RES-JB
    11. 6826
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technological advancements and innovations

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

    No Comments

    Negative Logits
     disgrace
    -0.74
     Isles
    -0.73
    Ire
    -0.70
     lockout
    -0.67
     Ethnic
    -0.67
     Cust
    -0.66
    guard
    -0.66
     FSA
    -0.65
     Holiday
    -0.64
     Loyal
    -0.63
    POSITIVE LOGITS
     graphene
    1.14
     breakthrough
    1.03
     physicists
    1.02
     prototypes
    0.98
     nanop
    0.97
     biom
    0.97
    velength
    0.96
     sensors
    0.91
     engineers
    0.91
     nano
    0.91
    Activations Density 0.928%

    No Known Activations