INDEX

Explanations

phrases related to conflict, law enforcement, and accountability

oai_token-act-pair · gpt-3.5-turbo

mentions of information or infamy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Blitz

-0.76

å§«

-0.70

ãĤ®

-0.64

 Boll

-0.63

VICE

-0.62

xus

-0.62

Accessory

-0.61

hyde

-0.61

EMENT

-0.61

WithNo

-0.61

POSITIVE LOGITS

requent

1.24

ighting

1.23

idelity

1.21

rast

1.19

latable

1.18

ractions

1.17

ortunately

1.17

erno

1.16

usions

1.15

requently

1.15

Activations Density 0.016%

phrases related to conflict, law enforcement, and accountability

mentions of information or infamy

No Comments

No Known Activations