INDEX

Explanations

words related to conflict, warfare, and combat

oai_token-act-pair · gpt-3.5-turbo

phrases related to military actions and conflicts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Pip

-0.70

 Username

-0.63

ips

-0.62

 Halls

-0.61

icken

-0.61

username

-0.61

 sisters

-0.60

cation

-0.60

icians

-0.60

gnu

-0.59

POSITIVE LOGITS

 havoc

0.95

ãĥ£

0.90

 ACTION

0.84

Attack

0.80

CLAIM

0.76

 revenge

0.76

NING

0.75

URN

0.71

orney

0.71

 Attacks

0.71

Activations Density 0.117%

words related to conflict, warfare, and combat

phrases related to military actions and conflicts

No Comments

No Known Activations