INDEX

Explanations

statements or declarations made by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stated."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

vernment

-0.68

brance

-0.67

iling

-0.66

apps

-0.65

alos

-0.64

abies

-0.64

 sacked

-0.64

illard

-0.64

 Cats

-0.64

marine

-0.62

POSITIVE LOGITS

gow

0.95

 stated

0.94

 mentions

0.76

 stating

0.76

 bluntly

0.75

WER

0.72

:]

0.72

TextColor

0.72

 indicates

0.71

:"

0.71

Activations Density 0.022%

statements or declarations made by individuals

instances of the word "stated."

No Comments

No Known Activations