INDEX

Explanations

words related to lurking or hiding

oai_token-act-pair · gpt-3.5-turbo

references to the location and actions associated with the term "lur."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

insula

-0.78

agne

-0.77

rod

-0.75

rification

-0.71

Ģ

-0.71

endered

-0.69

helm

-0.69

 Breaker

-0.68

ulsion

-0.67

knife

-0.67

POSITIVE LOGITS

ity

0.81

atility

0.78

atile

0.74

mere

0.69

heny

0.68

inately

0.66

vous

0.65

lin

0.62

cano

0.62

aced

0.61

Activations Density 0.078%

words related to lurking or hiding

references to the location and actions associated with the term "lur."

No Comments

No Known Activations