INDEX

Explanations

phrases related to specific names or terms

oai_token-act-pair · gpt-3.5-turbo

instances of a specific symbol or character

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

anwhile

-0.80

ctors

-0.65

EStream

-0.64

lda

-0.64

 tremend

-0.64

 eleph

-0.63

creen

-0.63

romy

-0.63

bye

-0.62

omething

-0.61

POSITIVE LOGITS

Â¯

0.95

¬

0.87

į

0.86

0.84

âĢł

0.82

¹

0.81

Â§

0.80

âĹ¼

0.76

Â¯Â¯Â¯Â¯

0.74

ı

0.72

Activations Density 0.271%

phrases related to specific names or terms

instances of a specific symbol or character

No Comments

No Known Activations