INDEX

Explanations

mentions of influential or prominent figures or entities

oai_token-act-pair · gpt-3.5-turbo

terms that signify prominence or leadership in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rehens

-0.71

ombies

-0.69

atron

-0.69

adas

-0.67

ascade

-0.67

nery

-0.67

thia

-0.67

aves

-0.67

afort

-0.64

tera

-0.64

POSITIVE LOGITS

quartered

0.84

wcs

0.80

better

0.79

boards

0.77

stone

0.77

 scorer

0.74

lines

0.73

 Leading

0.72

ership

0.72

 leading

0.70

Activations Density 0.020%

mentions of influential or prominent figures or entities

terms that signify prominence or leadership in various fields

No Comments

No Known Activations