INDEX

Explanations

mentioning or highlighting specific points, issues, or facts in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the act of stating or indicating something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

HER

-0.69

natureconservancy

-0.69

OOL

-0.67

 unfocusedRange

-0.61

 ILCS

-0.60

cum

-0.60

 seiz

-0.60

 Seym

-0.60

miah

-0.59

 Alive

-0.58

POSITIVE LOGITS

 fingers

0.89

 pointed

0.88

 toward

0.87

 towards

0.84

 finger

0.82

 pointing

0.81

 deduction

0.71

uers

0.70

 deductions

0.68

Points

0.68

Activations Density 0.030%

mentioning or highlighting specific points, issues, or facts in various contexts

phrases that indicate the act of stating or indicating something

No Comments

No Known Activations