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. 3024
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Cl" followed by a single character or multiple characters without a space in between

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Cl" in various contexts

    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
    terday
    -0.75
     htt
    -0.75
    shine
    -0.70
    ãĤ®
    -0.69
    BIP
    -0.67
     conclud
    -0.67
    ELL
    -0.66
    ãĥĨãĤ£
    -0.65
    BLIC
    -0.64
     è£ı
    -0.64
    POSITIVE LOGITS
    iff
    1.22
    ipper
    1.20
    iffs
    1.15
    utch
    1.15
    othes
    1.15
    oser
    1.14
    osures
    1.10
    amps
    1.06
    ients
    1.03
    asp
    1.02
    Activations Density 0.011%

    No Known Activations