INDEX

Explanations

references to movie ratings or reviews

oai_token-act-pair · gpt-3.5-turbo

mentions of notable names or entities, particularly related to specific organizations and individuals

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

istan

-0.86

umar

-0.75

population

-0.70

ially

-0.69

orescent

-0.68

cca

-0.68

iosity

-0.67

KER

-0.67

isin

-0.66

ively

-0.66

POSITIVE LOGITS

mic

0.68

Ĥ¬

0.68

old

0.66

apy

0.65

paces

0.63

rou

0.62

 Agenda

0.61

ythm

0.61

erver

0.60

ettings

0.60

Activations Density 0.073%

references to movie ratings or reviews

mentions of notable names or entities, particularly related to specific organizations and individuals

No Comments

No Known Activations