INDEX

Explanations

instances of the word "same" followed by a positive integer, indicating similarity or repetition

oai_token-act-pair · gpt-3.5-turbo

references to similarity or repetition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

*=-

-0.76

ONSORED

-0.72

rend

-0.72

orial

-0.71

 Democr

-0.70

 Provided

-0.70

 Lauder

-0.69

pac

-0.68

olate

-0.68

ç«

-0.67

POSITIVE LOGITS

 kinds

0.98

 thing

0.97

 exact

0.96

 amount

0.89

 sorts

0.88

 fate

0.88

 kind

0.84

 vein

0.81

ol

0.78

 sort

0.77

Activations Density 0.046%

instances of the word "same" followed by a positive integer, indicating similarity or repetition

references to similarity or repetition

No Comments

No Known Activations