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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13510
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical and ideological discussions, particularly those involving psychoanalysis and Marxism

    oai_token-act-pair · gpt-3.5-turbo

    references to psychoanalytic theory and its intersection with ideology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alert
    -0.87
    Boss
    -0.77
     VIP
    -0.76
    BALL
    -0.71
    Looks
    -0.71
    Pokemon
    -0.70
     registry
    -0.69
     paperwork
    -0.68
    Disable
    -0.68
     Trophy
    -0.68
    POSITIVE LOGITS
     philosophers
    1.20
     epist
    1.20
     philosoph
    1.12
    itatively
    1.08
     histor
    1.08
    icist
    1.03
     presupp
    1.03
     empir
    1.02
     philosopher
    1.00
     normative
    1.00
    Activations Density 0.520%

    No Known Activations