INDEX

Explanations

phrases related to being in the middle of something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "middle"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

orthy

-0.73

OUP

-0.68

vec

-0.68

edIn

-0.67

cci

-0.66

ilings

-0.64

illard

-0.64

undo

-0.64

 DRAG

-0.64

GV

-0.63

POSITIVE LOGITS

stad

0.79

hesis

0.73

 layer

0.69

 middle

0.69

middle

0.66

aday

0.65

 lane

0.64

uve

0.63

 Protestant

0.63

piece

0.62

Activations Density 0.012%

phrases related to being in the middle of something

occurrences of the word "middle"

No Comments

No Known Activations