© 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. 10-RES-JB
    11. 2781
    Prev
    Next
    INDEX
    Explanations

    names or specific terms starting with the letter "N"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'N'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     somewhere
    -0.65
     breeze
    -0.62
     tem
    -0.62
     Bapt
    -0.62
     unknow
    -0.59
     Rebels
    -0.57
     overe
    -0.57
     diplom
    -0.57
     Gibraltar
    -0.56
     rotor
    -0.55
    POSITIVE LOGITS
    aughty
    1.24
    onsense
    1.21
    umbered
    1.20
    ectar
    1.18
    ihil
    1.16
    ucle
    1.16
    ighth
    1.14
    ymph
    1.12
    umeric
    1.12
    autical
    1.11
    Activations Density 0.034%

    No Known Activations