INDEX

Explanations

phrases indicating statements or claims

oai_token-act-pair · gpt-3.5-turbo

phrases that denote various types of claims or assertions

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

NetMessage

-1.03

endars

-0.86

ockets

-0.86

pace

-0.79

undai

-0.79

events

-0.73

artifacts

-0.72

 contracting

-0.72

everal

-0.71

azeera

-0.70

POSITIVE LOGITS

ariat

0.83

 uttered

0.82

 echoed

0.81

 refrain

0.77

naire

0.75

 overlook

0.74

 regarding

0.74

 quote

0.73

 statement

0.73

 disclaimer

0.72

Activations Density 0.235%

phrases indicating statements or claims

phrases that denote various types of claims or assertions

No Comments

No Known Activations