INDEX

Explanations

instances where solutions or recommendations are being discussed or proposed

oai_token-act-pair · gpt-3.5-turbo

questions or phrases related to methods or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

krit

-0.84

uminati

-0.67

oven

-0.65

odium

-0.62

kan

-0.62

rored

-0.61

ãĤ©

-0.60

 Originally

-0.60

mingham

-0.59

ument

-0.59

POSITIVE LOGITS

to

1.17

 best

1.02

 should

0.90

soever

0.86

To

0.82

 constitutes

0.78

to

0.78

should

0.77

 appropriate

0.76

 thereto

0.75

Activations Density 0.120%

instances where solutions or recommendations are being discussed or proposed

questions or phrases related to methods or approaches

No Comments

No Known Activations