INDEX

Explanations

words implying concern or unease, such as "troubling" or "worrisome"

oai_token-act-pair · gpt-4-turbo

words related to negative evaluations or causing distress

oai_token-act-pair · gpt-3.5-turbo

terms indicating distressing or alarming situations

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

á

-0.86

tein

-0.84

cellence

-0.83

ighth

-0.83

oping

-0.77

arat

-0.76

©¶æ

-0.76

ersion

-0.75

ula

-0.75

haw

-0.75

POSITIVE LOGITS

 Seas

0.88

 worrisome

0.81

 Earthqu

0.81

ly

0.80

 newsp

0.77

LY

0.74

 Concern

0.74

 proble

0.73

Trend

0.73

 Tanz

0.72

Activations Density 0.014%

words implying concern or unease, such as "troubling" or "worrisome"

words related to negative evaluations or causing distress

terms indicating distressing or alarming situations

No Comments

No Known Activations