INDEX

Explanations

references to a specific entity named "Stars."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Stars" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vice

-0.73

ufact

-0.72

 Schne

-0.70

ADS

-0.65

uthor

-0.64

duction

-0.64

 millenn

-0.64

VICE

-0.63

TON

-0.62

PDATE

-0.61

POSITIVE LOGITS

cream

1.50

hips

1.32

ystem

0.98

bucks

0.96

burst

0.87

manship

0.85

light

0.84

ource

0.83

mith

0.83

peed

0.82

Activations Density 0.016%

references to a specific entity named "Stars."

mentions of "Stars" in various contexts

No Comments

No Known Activations