INDEX

Explanations

the word "bo" at different activation levels

oai_token-act-pair · gpt-3.5-turbo

words related to "bo" and its variations, indicating a focus on social behaviors or informal interactions

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

ivities

-0.74

 pige

-0.73

atio

-0.69

igators

-0.68

ow

-0.68

luck

-0.67

awar

-0.67

iquette

-0.66

REAM

-0.65

acious

-0.64

POSITIVE LOGITS

olean

1.16

vernment

1.04

zzi

0.98

xon

0.95

ption

0.88

ffer

0.86

zzle

0.85

å§«

0.85

pper

0.84

ptions

0.83

Activations Density 0.067%

the word "bo" at different activation levels

words related to "bo" and its variations, indicating a focus on social behaviors or informal interactions

No Comments

No Known Activations