INDEX

Explanations

instances where the term "threshold" is mentioned

oai_token-act-pair · gpt-3.5-turbo

references to specific thresholds and their implications in various contexts

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

ulf

-0.86

ateur

-0.70

iga

-0.67

fortune

-0.65

wagen

-0.63

thora

-0.62

ocation

-0.62

obbies

-0.62

asca

-0.61

arus

-0.61

POSITIVE LOGITS

 thresholds

0.91

 threshold

0.89

posts

0.85

 clearance

0.84

post

0.78

ansas

0.76

witz

0.74

 cutoff

0.71

pole

0.69

=$

0.69

Activations Density 0.033%

instances where the term "threshold" is mentioned

references to specific thresholds and their implications in various contexts

No Comments

No Known Activations