INDEX

Explanations

phrases related to placing someone or something in various situations or positions

oai_token-act-pair · gpt-3.5-turbo

the phrase "put in" and its variations related to placements and positions

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

xual

-0.68

ZA

-0.68

gets

-0.67

scl

-0.66

iasm

-0.65

Accessory

-0.63

TDs

-0.62

eds

-0.61

quel

-0.60

 Admission

-0.59

POSITIVE LOGITS

 jeopardy

0.85

ription

0.73

 ILCS

0.71

sole

0.70

 peril

0.67

atro

0.65

iris

0.65

 skim

0.65

intern

0.65

pload

0.62

Activations Density 0.114%

phrases related to placing someone or something in various situations or positions

the phrase "put in" and its variations related to placements and positions

No Comments

No Known Activations