INDEX

Explanations

words that are prefixed with 'un'

oai_token-act-pair · gpt-3.5-turbo

the prefix "un," indicating negation or reversal of meaning in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

OPLE

-0.94

uyomi

-0.84

anwhile

-0.81

hetti

-0.80

utical

-0.76

jriwal

-0.76

 Dynamics

-0.74

ãĥ¼ãĥĨãĤ£

-0.74

 Landing

-0.73

å§«

-0.71

POSITIVE LOGITS

balanced

1.13

ifying

1.03

confirmed

1.03

apolog

1.02

availability

0.99

assuming

0.98

cles

0.98

classified

0.98

interesting

0.96

quant

0.95

Activations Density 0.021%

words that are prefixed with 'un'

the prefix "un," indicating negation or reversal of meaning in words

No Comments

No Known Activations