INDEX

Explanations

words related to logic and reason

oai_token-act-pair · gpt-3.5-turbo

references to rationality

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

RAW

-0.79

ammy

-0.78

rael

-0.74

luster

-0.73

chin

-0.73

hold

-0.71

kick

-0.69

HI

-0.68

Nou

-0.68

IG

-0.68

POSITIVE LOGITS

izations

1.08

ization

0.99

isations

0.98

izes

0.95

tarian

0.95

iation

0.94

istic

0.94

izing

0.91

iated

0.86

ized

0.86

Activations Density 0.005%

words related to logic and reason

references to rationality

No Comments

No Known Activations