INDEX

Explanations

words related to being susceptible or predisposed to something

oai_token-act-pair · gpt-3.5-turbo

words indicating susceptibility or vulnerability to negative outcomes or conditions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tein

-0.85

row

-0.69

flies

-0.64

 towels

-0.63

assies

-0.59

 flashlight

-0.58

zos

-0.58

 Plat

-0.58

 torches

-0.58

 axes

-0.58

POSITIVE LOGITS

itability

0.81

Versions

0.76

 embr

0.76

theless

0.76

entious

0.75

ritis

0.72

 plagiar

0.72

icide

0.72

itable

0.72

wcs

0.71

Activations Density 0.055%

words related to being susceptible or predisposed to something

words indicating susceptibility or vulnerability to negative outcomes or conditions

No Comments

No Known Activations