INDEX

Explanations

the word "Besides" followed by additional information or an alternative perspective

oai_token-act-pair · gpt-3.5-turbo

the word "besides" and its variations indicating additional information or points

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

acy

-0.83

eway

-0.74

itory

-0.71

 charism

-0.68

ornia

-0.67

abolic

-0.66

iser

-0.65

cci

-0.64

ANS

-0.64

 descent

-0.64

POSITIVE LOGITS

ional

0.74

ãĥĦ

0.72

 Wond

0.72

lihood

0.69

words

0.67

 knowing

0.64

 ours

0.64

 contributing

0.63

xon

0.63

 serving

0.62

Activations Density 0.008%

the word "Besides" followed by additional information or an alternative perspective

the word "besides" and its variations indicating additional information or points

No Comments

No Known Activations