INDEX

Explanations

weapons or references to weapons

oai_token-act-pair · gpt-3.5-turbo

references to weapons

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

noon

-0.73

fo

-0.72

sis

-0.71

 Lank

-0.70

eff

-0.69

 Beckham

-0.67

 Salt

-0.67

 Woodward

-0.67

Cow

-0.66

awk

-0.66

POSITIVE LOGITS

 weapon

1.15

weapon

1.00

 weapons

0.99

 salute

0.91

 arsenal

0.90

powder

0.87

 pistols

0.84

EStream

0.83

Weapons

0.82

 wielded

0.82

Activations Density 0.012%

weapons or references to weapons

references to weapons

No Known Activations