INDEX

Explanations

words related to distraction and refocusing attention

oai_token-act-pair · gpt-3.5-turbo

references to distraction or being distracted

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

iders

-0.72

nai

-0.67

cko

-0.61

tained

-0.60

WER

-0.59

code

-0.58

 Ibid

-0.57

kai

-0.57

itals

-0.57

ITH

-0.57

POSITIVE LOGITS

 distract

0.77

Lug

0.75

 attention

0.74

 distractions

0.74

ibility

0.74

 distracted

0.72

 distraction

0.72

ingly

0.71

ming

0.71

ertation

0.71

Activations Density 0.034%

words related to distraction and refocusing attention

references to distraction or being distracted

No Comments

No Known Activations