INDEX

Explanations

words related to animated actions or interactive controls

oai_token-act-pair · gpt-3.5-turbo

adjectives related to characteristics and effects

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

owship

-1.00

olicited

-0.95

ãģ®éŃĶ

-0.83

tower

-0.78

mouth

-0.78

under

-0.76

unders

-0.76

foreseen

-0.75

qv

-0.75

FORE

-0.74

POSITIVE LOGITS

ative

0.79

 mating

0.78

 advers

0.76

 measures

0.72

 minded

0.70

 easing

0.69

 effect

0.69

 pronoun

0.69

 Guinea

0.67

 Powers

0.67

Activations Density 0.064%

words related to animated actions or interactive controls

adjectives related to characteristics and effects

No Comments

No Known Activations