INDEX

Explanations

technical terms related to hardware and software optimization

oai_token-act-pair · gpt-3.5-turbo

elements related to numerical or rating-based evaluations

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

obar

-0.73

osaurus

-0.73

otin

-0.73

 Frie

-0.71

 colonists

-0.67

arians

-0.66

 Samar

-0.66

ocrats

-0.65

 Britons

-0.64

osaurs

-0.64

POSITIVE LOGITS

ãħĭ

1.14

[+

1.09

ãħĭãħĭ

1.01

ã

0.83

rating

0.82

/-

0.82

Ĺ

0.78

Ļ½

0.75

rated

0.73

fecture

0.72

Activations Density 0.010%

technical terms related to hardware and software optimization

elements related to numerical or rating-based evaluations

No Comments

No Known Activations