INDEX

Explanations

acronyms related to intellectual property

oai_token-act-pair · gpt-3.5-turbo

references to intellectual property (IP)

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

ufact

-0.84

puter

-0.82

taboola

-0.77

ãĤ£

-0.75

 Tsukuyomi

-0.74

 Jenner

-0.73

 Chatt

-0.72

 Gors

-0.72

 Crusher

-0.72

andise

-0.72

POSITIVE LOGITS

HER

0.97

PLE

0.94

HY

0.89

MU

0.87

ython

0.86

artisan

0.86

otent

0.85

osit

0.85

PLIED

0.85

sych

0.85

Activations Density 0.006%

acronyms related to intellectual property

references to intellectual property (IP)

No Comments

No Known Activations