INDEX

Explanations

verbs related to taking action or making decisions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating goals or objectives

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

abad

-0.74

aspers

-0.72

IQ

-0.65

okia

-0.65

ashtra

-0.64

JP

-0.64

é¾įå¥ĳå£«

-0.63

ccording

-0.63

dependent

-0.63

¿½

-0.62

POSITIVE LOGITS

liest

0.93

ggles

0.70

Ney

0.65

ked

0.64

elight

0.64

rium

0.63

 nearest

0.62

 oneself

0.61

gery

0.61

]),

0.61

Activations Density 0.313%

verbs related to taking action or making decisions

phrases indicating goals or objectives

No Comments

No Known Activations