© 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. 22562
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that are pending or not yet completed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or states that are yet to occur

    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
    Choice
    -0.71
    didn
    -0.71
    ARP
    -0.69
    Tur
    -0.68
     Fortress
    -0.66
    john
    -0.65
    soDeliveryDate
    -0.64
    pill
    -0.64
    easy
    -0.64
     Veh
    -0.63
    POSITIVE LOGITS
     arrive
    1.03
     confirm
    1.02
     settle
    1.02
     formally
    1.01
     receive
    1.01
     disclose
    1.00
     officially
    0.99
     prove
    0.98
     recover
    0.96
     establish
    0.96
    Activations Density 0.065%

    No Known Activations