© 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. 928
    Prev
    Next
    INDEX
    Explanations

    figures or objects positioned in specific ways, such as left to right, above, etc

    oai_token-act-pair · gpt-3.5-turbo

    textual elements related to spatial orientation or positioning

    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
    Ĥª
    -0.81
    API
    -0.79
    76561
    -0.77
    comed
    -0.75
    477
    -0.72
    ©¶æ¥µ
    -0.71
    imet
    -0.71
    bill
    -0.70
    ib
    -0.69
    conom
    -0.69
    POSITIVE LOGITS
     bottom
    1.22
     centre
    1.16
     center
    1.14
     middle
    1.09
     srfAttach
    1.08
     left
    1.01
     underside
    1.00
     rear
    0.99
     top
    0.99
     aft
    0.97
    Activations Density 0.354%

    No Known Activations