INDEX

Explanations

instances where someone is noticing or being noticed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "notice" and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raft

-0.80

sis

-0.78

adr

-0.76

ulum

-0.74

quer

-0.74

export

-0.72

venge

-0.72

uga

-0.71

prep

-0.70

wives

-0.70

POSITIVE LOGITS

how

0.88

 discrepancies

0.78

 similarities

0.76

flies

0.71

 inconsistencies

0.71

 noticing

0.70

 spikes

0.68

 something

0.68

 Improvement

0.67

 noticed

0.66

Activations Density 0.034%

instances where someone is noticing or being noticed

instances of the word "notice" and its variations

No Comments

No Known Activations