INDEX

Explanations

terms related to nuclear disarmament

oai_token-act-pair · gpt-3.5-turbo

terms related to disarmament and nuclear non-proliferation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Preferred

-0.70

ALE

-0.68

Lear

-0.68

iott

-0.68

 Opportunity

-0.68

 Trader

-0.68

Ear

-0.67

 Variant

-0.67

 Quadro

-0.66

BUR

-0.66

POSITIVE LOGITS

 disarm

1.11

achev

0.96

ament

0.93

ptives

0.88

atures

0.84

ascus

0.82

aments

0.82

merce

0.81

locking

0.80

ufact

0.80

Activations Density 0.038%

terms related to nuclear disarmament

terms related to disarmament and nuclear non-proliferation

No Comments

No Known Activations