INDEX

Explanations

phrases indicating uncertainty or lack of knowledge

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or lack of knowledge

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alde

-0.71

eneg

-0.70

aqu

-0.68

ricanes

-0.68

don

-0.68

woods

-0.65

hari

-0.64

si

-0.64

heast

-0.63

eder

-0.63

POSITIVE LOGITS

ually

1.06

 idea

0.80

yout

0.73

uren

0.73

 moot

0.68

 accelerator

0.67

reprene

0.67

urally

0.66

 Idea

0.66

 concept

0.65

Activations Density 0.016%

phrases indicating uncertainty or lack of knowledge

expressions of uncertainty or lack of knowledge

No Comments

No Known Activations