Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 44
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions happening in the past

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to controversial or judgmental evaluations of individuals

    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
    )).
    -0.66
    é¾įå
    -0.58
    ļé
    -0.56
    rush
    -0.56
    )."
    -0.55
    aldo
    -0.55
    ]).
    -0.54
    CONCLUS
    -0.53
    thouse
    -0.53
    ))))
    -0.52
    POSITIVE LOGITS
    Picture
    0.65
     firsthand
    0.54
    ickr
    0.49
     its
    0.49
    ,[
    0.49
     because
    0.49
     their
    0.48
     overseas
    0.47
     vitro
    0.47
    because
    0.47
    Activations Density 1.535%

    No Known Activations