INDEX

Explanations

instances of the word "the" with varying emphasis levels based on context

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

leground

-0.74

ielding

-0.73

 thereby

-0.72

Whether

-0.71

agger

-0.70

 amid

-0.68

-0.67

ģĸ

-0.67

Develop

-0.67

 borne

-0.66

POSITIVE LOGITS

 coolest

1.18

 pics

1.04

guy

1.01

 damn

0.98

 fuck

0.96

 slightest

0.95

 whole

0.93

 shitty

0.92

 shit

0.91

 crap

0.89

Activations Density 0.550%

instances of the word "the" with varying emphasis levels based on context

occurrences of the word "the" in various contexts

No Comments

No Known Activations