INDEX

Explanations

phrases indicating demonstration or revelation

oai_token-act-pair · gpt-3.5-turbo

instances of the verb "show" and its variations, indicating demonstration or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ades

-0.72

pour

-0.70

 livest

-0.69

kson

-0.68

agues

-0.67

 freezes

-0.67

porary

-0.66

accompanied

-0.66

ascus

-0.66

atri

-0.66

POSITIVE LOGITS

how

0.96

 disrespect

0.83

 weakness

0.82

 appreciation

0.80

 maturity

0.79

why

0.76

 incompetence

0.74

 impat

0.74

how

0.72

 ignorance

0.72

Activations Density 0.119%

phrases indicating demonstration or revelation

instances of the verb "show" and its variations, indicating demonstration or evidence

No Comments

No Known Activations