INDEX

Explanations

organization names or acronyms

oai_token-act-pair · gpt-3.5-turbo

mentions of specific organizations or entities, particularly those abbreviated with "OC"

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

 Gork

-0.76

 Uriel

-0.73

things

-0.71

 Friedman

-0.69

 Brah

-0.67

 Witt

-0.66

dab

-0.65

 Somers

-0.65

selves

-0.64

ãĥĢ

-0.63

POSITIVE LOGITS

ombat

1.14

ontent

1.10

ategory

1.08

OPS

1.00

culus

1.00

OC

0.98

onut

0.97

urrencies

0.97

ycle

0.95

ourage

0.94

Activations Density 0.018%

organization names or acronyms

mentions of specific organizations or entities, particularly those abbreviated with "OC"

No Comments

No Known Activations