INDEX

Explanations

instances of the term "overtime" and related phrases

oai_token-act-pair · gpt-3.5-turbo

instances of the word "overtime" in the context of work-related discussions

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

ystem

-0.82

sonian

-0.79

âĸ¬

-0.73

ydia

-0.73

=-=-=-=-=-=-=-=-

-0.72

gling

-0.72

;;;;;;;;

-0.68

chu

-0.67

kie

-0.67

friend

-0.67

POSITIVE LOGITS

 overtime

0.85

rites

0.75

uty

0.72

 penalty

0.70

 msec

0.68

 Dragonbound

0.68

 accrued

0.67

 duties

0.66

 stopp

0.64

 earnings

0.63

Activations Density 0.062%

instances of the term "overtime" and related phrases

instances of the word "overtime" in the context of work-related discussions

No Comments

No Known Activations