INDEX

Explanations

persons wielding knives or being involved in knife-related actions or conflicts

oai_token-act-pair · gpt-3.5-turbo

references to knives and related actions or contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ICAN

-0.84

mberg

-0.84

bos

-0.81

ICLE

-0.73

rian

-0.72

ALS

-0.71

tainment

-0.71

oday

-0.70

leep

-0.68

tz

-0.67

POSITIVE LOGITS

 blades

1.14

 blade

1.12

 scissors

1.05

 wielded

1.03

 knives

0.99

 knife

0.94

blade

0.93

 wielding

0.91

 dagger

0.90

 claws

0.89

Activations Density 0.079%

persons wielding knives or being involved in knife-related actions or conflicts

references to knives and related actions or contexts

No Comments

No Known Activations