INDEX

Explanations

sentences ending with "said"

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 decomp

-0.85

 Marble

-0.76

 Myster

-0.75

 Discord

-0.73

 Nept

-0.72

 Voyager

-0.71

 Manhattan

-0.70

 clutter

-0.70

 gray

-0.69

 warp

-0.68

POSITIVE LOGITS

¬

0.97

¹

0.97

£

0.96

į

0.95

Asia

0.92

ais

0.92

Į

0.90

AFP

0.90

Iraq

0.87

ech

0.87

Activations Density 0.427%

sentences ending with "said"

special characters or symbols in the text

No Comments

No Known Activations