INDEX

Explanations

phrases indicating something is excessive or extreme

oai_token-act-pair · gpt-3.5-turbo

phrases that express limitations or conditions that are "too" extreme

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

 largeDownload

-0.77

escal

-0.72

ãĤ¢ãĥ«

-0.71

kind

-0.71

ãĥĨ

-0.65

ãĤ¼

-0.65

iste

-0.64

ãĥ©ãĥ³

-0.64

TPP

-0.63

written

-0.62

POSITIVE LOGITS

 anymore

0.77

 warrant

0.73

 foreseeable

0.71

 adequately

0.71

 anything

0.71

 feas

0.71

 Spoon

0.68

rists

0.68

 necessarily

0.66

 qualify

0.65

Activations Density 0.069%

phrases indicating something is excessive or extreme

phrases that express limitations or conditions that are "too" extreme

No Comments

No Known Activations