INDEX

Explanations

instances of the word "poised"

oai_token-act-pair · gpt-3.5-turbo

the word "poised" and variations related to readiness or potential future actions

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

EVA

-0.67

friend

-0.65

friends

-0.64

cause

-0.62

orders

-0.62

bey

-0.62

clusive

-0.61

ilitating

-0.61

tein

-0.61

natureconservancy

-0.61

POSITIVE LOGITS

 unbeliev

0.78

rons

0.75

cture

0.74

olicy

0.73

imately

0.68

 poised

0.68

eous

0.68

 perspect

0.66

atility

0.66

abouts

0.66

Activations Density 0.014%

instances of the word "poised"

the word "poised" and variations related to readiness or potential future actions

No Comments

No Known Activations