INDEX

Explanations

HTML or programming-related terms and specific keywords within code snippets

oai_token-act-pair · gpt-3.5-turbo

technical terms related to targeted processes or operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ophon

-0.76

GMT

-0.69

atorium

-0.67

iddy

-0.65

erd

-0.64

atron

-0.64

rl

-0.63

âķĲâķĲ

-0.63

ulton

-0.62

é¾įåĸļå£«

-0.62

POSITIVE LOGITS

 adversaries

0.94

 attacker

0.85

 aggress

0.84

foe

0.83

 Allies

0.82

 attackers

0.80

 foes

0.78

 defenses

0.76

 adversary

0.76

sov

0.75

Activations Density 0.501%

HTML or programming-related terms and specific keywords within code snippets

technical terms related to targeted processes or operations

No Comments

No Known Activations