INDEX

Explanations

numbers with high values

oai_token-act-pair · gpt-3.5-turbo

numerical values, particularly large numbers and monetary amounts

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

orate

-0.82

lict

-0.81

bara

-0.80

inges

-0.79

nels

-0.76

essa

-0.76

acia

-0.74

lying

-0.74

inately

-0.74

nih

-0.73

POSITIVE LOGITS

 ILCS

0.98

MHz

0.94

SourceFile

0.81

æ©Ł

0.80

MHz

0.79

0.71

OPLE

0.71

bps

0.70

ãĥ³ãĤ¸

0.70

0.67

Activations Density 0.055%

numbers with high values

numerical values, particularly large numbers and monetary amounts

No Comments

No Known Activations