INDEX

Explanations

text related to various skills, such as skill-building, skill sets, knowledge, and expertise

oai_token-act-pair · gpt-3.5-turbo

mentions of skills and abilities in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

iatus

-0.88

idays

-0.77

ipel

-0.74

autions

-0.73

scription

-0.72

iversary

-0.70

delete

-0.70

cott

-0.70

levard

-0.70

OPA

-0.70

POSITIVE LOGITS

 skills

1.26

 skill

1.25

 proficiency

1.19

 knack

1.19

 talents

1.18

 physique

1.16

 agility

1.16

 talent

1.10

 abilities

1.07

 mastery

1.07

Activations Density 0.716%

text related to various skills, such as skill-building, skill sets, knowledge, and expertise

mentions of skills and abilities in various contexts

No Comments

No Known Activations