INDEX

Explanations

words related to weaknesses and flaws, especially in a critical context

oai_token-act-pair · gpt-3.5-turbo

terms related to flaws, weaknesses, and deficiencies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

rollers

-0.90

iversary

-0.82

ctors

-0.73

winner

-0.70

ramid

-0.70

amaz

-0.69

cise

-0.68

da

-0.68

urai

-0.66

rooms

-0.65

POSITIVE LOGITS

 inherent

1.12

 flaws

1.05

 plag

1.03

 weaknesses

0.97

 vulnerabilities

0.88

 deficiencies

0.87

 flaw

0.86

ibilities

0.86

ulner

0.78

 underlying

0.77

Activations Density 0.129%

words related to weaknesses and flaws, especially in a critical context

terms related to flaws, weaknesses, and deficiencies

No Comments

No Known Activations