INDEX

Explanations

superlatives related to quantity or degree

oai_token-act-pair · gpt-3.5-turbo

descriptors of effort and capacity related to accomplishments and challenges

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

ucky

-0.66

 quint

-0.66

 Deadly

-0.63

CHAT

-0.63

 Tactics

-0.62

ħĭ

-0.62

-0.60

 Representative

-0.60

 Hort

-0.58

CST

-0.58

POSITIVE LOGITS

 nowadays

0.75

Ùĩ

0.71

uable

0.69

 âĶľ

0.68

 hoop

0.67

 lately

0.67

catentry

0.66

(>

0.66

 involved

0.65

 headaches

0.65

Activations Density 0.291%

superlatives related to quantity or degree

descriptors of effort and capacity related to accomplishments and challenges

No Comments

No Known Activations