INDEX

Explanations

phrases related to obstruction or preventing something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "block" and its variations, indicating obstacles or barriers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rious

-0.80

BUS

-0.67

mble

-0.66

lli

-0.66

 Volunte

-0.65

Rust

-0.64

lycer

-0.62

enture

-0.62

MIC

-0.61

 prest

-0.61

POSITIVE LOGITS

aded

1.09

buster

1.06

ades

1.04

quote

0.98

ading

0.96

busters

0.94

ade

0.89

 access

0.78

chains

0.76

aders

0.75

Activations Density 0.037%

phrases related to obstruction or preventing something

instances of the word "block" and its variations, indicating obstacles or barriers

No Comments

No Known Activations