INDEX

Explanations

phrases related to a specific policy concept

oai_token-act-pair · gpt-3.5-turbo

special characters or encodings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shrouded

-0.74

 cyan

-0.73

 collecting

-0.71

 coast

-0.70

 dirt

-0.70

 decomp

-0.70

 sofa

-0.68

 smokes

-0.68

 buggy

-0.68

 minim

-0.67

POSITIVE LOGITS

º

0.96

£

0.89

 Conversely

0.87

¹

0.86

Footnote

0.85

gypt

0.84

ĸļ

0.84

fn

0.83

Ī

0.83

ONSORED

0.82

Activations Density 0.171%

phrases related to a specific policy concept

special characters or encodings

No Comments

No Known Activations