INDEX

Explanations

words related to authority and command

oai_token-act-pair · gpt-3.5-turbo

terms related to military command and hierarchy

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

OHN

-0.78

Prev

-0.69

 Happ

-0.67

Versions

-0.66

 Bloom

-0.64

rencies

-0.64

 Indust

-0.62

RAG

-0.62

Gamer

-0.62

Mini

-0.61

POSITIVE LOGITS

eering

1.16

eer

1.02

eers

1.02

nance

0.89

ership

0.88

aining

0.87

hammer

0.87

eur

0.87

 commands

0.84

ained

0.83

Activations Density 0.021%

words related to authority and command

terms related to military command and hierarchy

No Comments

No Known Activations