INDEX

Explanations

verbs related to changing or customizing, especially in a technical or software context

oai_token-act-pair · gpt-3.5-turbo

attributes and options related to customization

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

çĶ°

-0.83

¿

-0.80

æĸ

-0.78

nea

-0.76

ç«

-0.76

Ur

-0.76

Ø±

-0.74

NY

-0.73

-0.70

Fear

-0.70

POSITIVE LOGITS

 combinations

1.08

 individually

1.04

 customize

0.99

 variations

0.98

 configurations

0.97

 sorts

0.97

 variables

0.95

 freely

0.95

 kinds

0.94

 options

0.94

Activations Density 0.474%

verbs related to changing or customizing, especially in a technical or software context

attributes and options related to customization

No Comments

No Known Activations