INDEX

Explanations

adjectives related to wisdom or intelligence

oai_token-act-pair · gpt-3.5-turbo

phrases expressing wisdom or wise decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

alogue

-0.77

packages

-0.73

yip

-0.73

 Gutenberg

-0.71

 Robots

-0.70

 shale

-0.69

ĸļ

-0.68

hedral

-0.68

ategory

-0.67

isite

-0.65

POSITIVE LOGITS

guy

0.98

 counsel

0.90

 advice

0.82

man

0.82

ness

0.81

lings

0.81

 Advice

0.78

eyed

0.78

comm

0.77

ly

0.77

Activations Density 0.027%

adjectives related to wisdom or intelligence

phrases expressing wisdom or wise decision-making

No Comments

No Known Activations