INDEX

Explanations

words related to toxic chemicals or substances

oai_token-act-pair · gpt-3.5-turbo

terms related to pesticides and herbicides

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

herty

-0.81

arel

-0.79

isl

-0.75

roud

-0.72

ALE

-0.71

 Lumpur

-0.71

¶

-0.71

ordan

-0.69

 Gutenberg

-0.67

urn

-0.64

POSITIVE LOGITS

icides

1.20

icide

1.18

osate

0.95

oxide

0.85

icidal

0.83

gency

0.75

 batt

0.74

 poisoning

0.73

ionage

0.72

 extermin

0.72

Activations Density 0.008%

words related to toxic chemicals or substances

terms related to pesticides and herbicides

No Comments

No Known Activations