INDEX

Explanations

excitement and anticipation-related words or phrases

oai_token-act-pair · gpt-3.5-turbo

expressions of excitement and enthusiasm

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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ledge

-0.97

loo

-0.84

-0.79

yip

-0.75

hip

-0.74

fall

-0.73

fully

-0.70

ful

-0.68

lez

-0.66

Tec

-0.66

POSITIVE LOGITS

Reviewer

0.88

udic

0.86

amel

0.81

pty

0.78

ocument

0.77

Exc

0.73

osc

0.72

umph

0.71

isd

0.70

USE

0.70

Activations Density 0.055%

excitement and anticipation-related words or phrases

expressions of excitement and enthusiasm

No Comments

No Known Activations