INDEX

Explanations

mentions of the name "Milton"

oai_token-act-pair · gpt-3.5-turbo

mentions of the names "Milton" and "Mont," likely referring to specific people or locations

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

uler

-0.79

ements

-0.79

venants

-0.77

eker

-0.76

cial

-0.73

cks

-0.72

hiro

-0.72

orge

-0.70

vol

-0.69

Magikarp

-0.69

POSITIVE LOGITS

aneously

0.99

aneous

0.84

INGTON

0.75

 Keynes

0.75

 Gardens

0.69

 Wynne

0.68

elta

0.66

 Dresden

0.64

ipop

0.64

 Virtue

0.63

Activations Density 0.049%

mentions of the name "Milton"

mentions of the names "Milton" and "Mont," likely referring to specific people or locations

No Comments

No Known Activations