© 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. 8-RES-JB
    11. 2528
    Prev
    Next
    INDEX
    Explanations

    phrases indicating effort or dedication towards a task or goal

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "put in" or similar constructions indicating effort or contribution

    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
    =]
    -0.76
    catentry
    -0.67
    LM
    -0.65
    Ħ¢
    -0.64
    ALE
    -0.64
    NOW
    -0.63
    Ring
    -0.63
    FACE
    -0.62
    %%
    -0.62
    "]=>
    -0.62
    POSITIVE LOGITS
    ordinate
    1.01
     lieu
    0.88
    apt
    0.79
     somew
    0.77
    umbn
    0.75
    oki
    0.74
     unison
    0.72
    esville
    0.72
     excess
    0.70
     reinforcements
    0.65
    Activations Density 0.048%

    No Known Activations