© 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. 3-RES-JB
    11. 8160
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that occur or decisions that are made "after" a certain event or condition

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the term "after" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.76
    cci
    -0.70
    NRS
    -0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.65
    aq
    -0.64
    eto
    -0.63
    odiac
    -0.63
    ����
    -0.60
    voy
    -0.60
    ours
    -0.60
    POSITIVE LOGITS
    market
    1.02
    noon
    1.02
     finishing
    0.86
    word
    0.83
    thought
    0.82
    wards
    0.80
     completing
    0.80
     consulting
    0.79
     purchasing
    0.78
     acquiring
    0.78
    Activations Density 0.115%

    No Known Activations