© 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. 1-RES-JB
    11. 9398
    Prev
    Next
    INDEX
    Explanations

    names of people or places related to corporate or financial activities

    oai_token-act-pair · gpt-3.5-turbo

    the name "Sz" appearing in different contexts or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glou
    -0.65
     totality
    -0.62
    aneously
    -0.61
     Hurricanes
    -0.61
    TAIN
    -0.61
    naissance
    -0.60
     pediatric
    -0.59
    ously
    -0.59
    ACTED
    -0.58
     checkout
    -0.58
    POSITIVE LOGITS
     Sz
    1.43
    ittal
    1.00
    cz
    0.98
    ansky
    0.98
    ÅĤ
    0.84
    opes
    0.82
    umo
    0.82
    Gy
    0.81
    Pi
    0.81
    anski
    0.80
    Activations Density 0.004%

    No Known Activations