INDEX

Explanations

mentions of expansion or increase in size, scope, or range

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "expansion" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Ķ

-0.72

âķĲâķĲ

-0.72

rol

-0.70

MET

-0.69

=-=-=-=-=-=-=-=-

-0.69

ched

-0.68

yer

-0.68

 Alps

-0.67

lihood

-0.67

bane

-0.66

POSITIVE LOGITS

 expansion

1.20

 expansions

1.09

ansion

0.90

 enlarg

0.85

 specialization

0.81

 colonization

0.77

 promotion

0.77

arily

0.73

 creep

0.73

oing

0.73

Activations Density 0.010%

mentions of expansion or increase in size, scope, or range

references to the concept of "expansion" in various contexts

No Comments

No Known Activations