INDEX

Explanations

high-ranking corporate titles such as executives and graduates from higher education programs

oai_token-act-pair · gpt-3.5-turbo

terms related to executive positions and educational degrees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

FUL

-0.79

theless

-0.76

ppo

-0.75

Klu

-0.70

EEEE

-0.69

poke

-0.67

veyard

-0.67

TPS

-0.66

 Stre

-0.65

 Fruit

-0.64

POSITIVE LOGITS

 exec

1.20

ials

0.83

 alum

0.82

lisher

0.79

aution

0.79

rats

0.78

rities

0.78

iations

0.78

inarily

0.75

 cout

0.75

Activations Density 0.008%

high-ranking corporate titles such as executives and graduates from higher education programs

terms related to executive positions and educational degrees

No Comments

No Known Activations