INDEX

Explanations

technical terms related to data processing and control in systems

oai_token-act-pair · gpt-3.5-turbo

mathematical concepts and processes

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

 millenn

-0.63

 resurg

-0.62

 looph

-0.61

 whistleblowers

-0.60

ccording

-0.59

udos

-0.58

 reluct

-0.57

 fortun

-0.56

 prosecutions

-0.56

theless

-0.53

POSITIVE LOGITS

/(

0.70

\'

0.65

(/

0.64

().

0.63

or

0.61

 âĨĴ

0.61

(=

0.61

->

0.60

 interval

0.58

 cycle

0.58

Activations Density 0.864%

technical terms related to data processing and control in systems

mathematical concepts and processes

No Comments

No Known Activations