INDEX

Explanations

items or actions related to knives

oai_token-act-pair · gpt-3.5-turbo

references to knives in various contexts

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

mberg

-0.84

phas

-0.78

rians

-0.74

rian

-0.73

rix

-0.73

auri

-0.68

alse

-0.68

 Emin

-0.67

nces

-0.66

ysical

-0.65

POSITIVE LOGITS

 scissors

1.09

 blade

1.04

 blades

0.99

knife

0.99

 wielded

0.94

 knife

0.92

 knives

0.92

 claws

0.91

edge

0.89

 cutter

0.88

Activations Density 0.043%

items or actions related to knives

references to knives in various contexts

No Comments

No Known Activations