INDEX

Explanations

direct quotations in text

oai_token-act-pair · gpt-3.5-turbo

statements that reference quotes and attributions

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kt

-0.64

brance

-0.63

cycle

-0.62

ãĥĺ

-0.60

hemer

-0.59

light

-0.59

Visit

-0.59

Join

-0.59

BOX

-0.59

 Medals

-0.58

POSITIVE LOGITS

 saying

0.91

 Saying

0.80

 citing

0.79

terday

0.78

 describing

0.76

 explaining

0.75

ulin

0.74

 cited

0.74

 sounding

0.70

 stating

0.70

Activations Density 0.087%

direct quotations in text

statements that reference quotes and attributions

No Comments

No Known Activations