© 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. 8-RES-JB
    11. 15094
    Prev
    Next
    INDEX
    Explanations

    words related to captivating or intense experiences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to capturing or being captured

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trust
    -0.67
    sterdam
    -0.65
     onwards
    -0.64
     partnership
    -0.64
     reconciliation
    -0.63
     Catalyst
    -0.63
     paternity
    -0.62
     spare
    -0.62
     prone
    -0.61
     Tend
    -0.61
    POSITIVE LOGITS
    ivating
    1.38
    aining
    1.33
    ained
    1.31
    ains
    1.27
    ivated
    1.18
    ions
    1.13
    iors
    1.09
    oise
    1.07
    orable
    1.07
    ured
    1.04
    Activations Density 0.036%

    No Known Activations