INDEX

Explanations

phrases related to news headlines or events

oai_token-act-pair · gpt-3.5-turbo

colons followed by titles or headings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mone

-0.76

license

-0.68

goo

-0.67

mort

-0.67

authorized

-0.66

 veter

-0.66

EEK

-0.65

ISON

-0.65

ICLE

-0.65

stellar

-0.65

POSITIVE LOGITS

 Photograph

0.88

 Pict

0.79

 Protesters

0.77

 Buckingham

0.76

 Ahead

0.75

 Scenes

0.74

 Irwin

0.74

 Robbie

0.74

 Garry

0.74

Ian

0.73

Activations Density 0.059%

phrases related to news headlines or events

colons followed by titles or headings

No Comments

No Known Activations