© 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. 2-RES-JB
    11. 9261
    Prev
    Next
    INDEX
    Explanations

    phrases related to suggesting playing or engagement in some activity

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people's names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.77
    braska
    -0.76
    flix
    -0.69
    ?]
    -0.68
    cephal
    -0.68
    aughs
    -0.68
    \">
    -0.66
    pes
    -0.65
    oiler
    -0.65
    oen
    -0.64
    POSITIVE LOGITS
    ilon
    0.72
     Soviets
    0.68
    olver
    0.64
    åİ
    0.64
     cosmic
    0.63
     outgoing
    0.63
    lan
    0.63
    Magikarp
    0.62
    eral
    0.62
     Lans
    0.61
    Activations Density 0.000%

    No Known Activations