INDEX

Explanations

phrases related to actions taken or things happening sequentially

oai_token-act-pair · gpt-3.5-turbo

phrases indicating sequential actions or processes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 GEAR

-0.73

MAP

-0.72

Jam

-0.71

Ü

-0.70

Greek

-0.69

Parts

-0.66

ãĥĨ

-0.66

Bon

-0.65

Marginal

-0.65

atican

-0.64

POSITIVE LOGITS

ousand

0.74

teenth

0.71

pload

0.70

yip

0.70

laus

0.69

handed

0.69

ledged

0.65

eeper

0.65

ucha

0.64

rir

0.64

Activations Density 0.160%

phrases related to actions taken or things happening sequentially

phrases indicating sequential actions or processes

No Comments

No Known Activations