INDEX

Explanations

proper nouns or acronyms

oai_token-act-pair · gpt-3.5-turbo

references to specific television or media networks and associated entities

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

pering

-0.88

rition

-0.81

met

-0.79

acters

-0.77

itarian

-0.74

portation

-0.73

plex

-0.73

ogeneity

-0.72

burg

-0.72

cent

-0.70

POSITIVE LOGITS

ND

0.98

 Seym

0.85

LR

0.75

req

0.73

oÄŁ

0.65

CAST

0.65

IFF

0.62

AY

0.60

ependent

0.60

MT

0.60

Activations Density 0.080%

proper nouns or acronyms

references to specific television or media networks and associated entities

No Comments

No Known Activations