INDEX

Explanations

words indicating a range or variation

oai_token-act-pair · gpt-3.5-turbo

phrases that describe a variety or range of subjects or conditions

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

advertisement

-0.81

IDA

-0.79

mit

-0.78

scape

-0.72

wards

-0.71

si

-0.71

driving

-0.71

bal

-0.71

eon

-0.71

Gold

-0.66

POSITIVE LOGITS

 ranging

1.05

 ranges

1.00

 ranged

0.88

 range

0.82

range

0.75

ranging

0.72

 lengths

0.71

ãĤ¤ãĥĪ

0.70

 Luxem

0.70

 spans

0.66

Activations Density 0.011%

words indicating a range or variation

phrases that describe a variety or range of subjects or conditions

No Comments

No Known Activations