INDEX

Explanations

phrases related to planned or coordinated activities

oai_token-act-pair · gpt-3.5-turbo

references to law enforcement or military operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

bitious

-0.73

eree

-0.69

 Marketable

-0.67

gets

-0.67

cknowled

-0.65

yi

-0.65

weet

-0.63

aez

-0.63

hus

-0.61

ioxide

-0.61

POSITIVE LOGITS

 operation

0.98

eering

0.85

ally

0.84

ional

0.84

Operation

0.84

operation

0.82

ION

0.78

ality

0.77

ions

0.75

 operations

0.73

Activations Density 0.015%

phrases related to planned or coordinated activities

references to law enforcement or military operations

No Comments

No Known Activations