INDEX

Explanations

references to specific organizations or entities with the acronym "AF"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the end of text marker and related abbreviations

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

 Morg

-0.74

 Vaugh

-0.71

 Boone

-0.67

igators

-0.66

 Gott

-0.64

Accessory

-0.64

 Limbaugh

-0.63

 Rollins

-0.63

 Blackwell

-0.62

ozo

-0.61

POSITIVE LOGITS

RIC

1.22

rica

0.99

ornia

0.99

SPA

0.95

RA

0.93

amily

0.90

rost

0.89

riend

0.87

FL

0.84

ECA

0.84

Activations Density 0.018%

references to specific organizations or entities with the acronym "AF"

occurrences of the end of text marker and related abbreviations

No Comments

No Known Activations