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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3405
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal suspects and police investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "suspect" in relation to criminal activity

    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
    unch
    -0.76
    UNCH
    -0.72
    galitarian
    -0.71
    ntil
    -0.68
    issance
    -0.68
    andel
    -0.67
    ummer
    -0.66
    owan
    -0.66
    ankind
    -0.65
    ollen
    -0.65
    POSITIVE LOGITS
     suspects
    0.83
     suspect
    0.77
     CSI
    0.68
     mishand
    0.68
    istani
    0.66
     perpetrator
    0.65
    itives
    0.65
     Snyder
    0.65
    ively
    0.65
     Tsarnaev
    0.64
    Activations Density 0.022%

    No Known Activations