INDEX

Explanations

specific symbols or indicators

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol, likely related to formatting or markup

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

 clad

-0.68

 cyan

-0.68

 collecting

-0.67

 Samar

-0.67

 touches

-0.66

 shroud

-0.66

 assemb

-0.64

 buggy

-0.63

bed

-0.63

 sitting

-0.63

POSITIVE LOGITS

£

0.95

¹

0.93

ONSORED

0.91

¬

0.87

į

0.86

gypt

0.85

º

0.85

Ĥ

0.84

ĸļ

0.82

aspx

0.82

Activations Density 0.133%

specific symbols or indicators

instances of a specific character or symbol, likely related to formatting or markup

No Comments

No Known Activations