INDEX

Explanations

instances of the word "Kam" followed by a numerical value of 9 or 10

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Kam" and its variations in context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãģį

-0.80

 checkout

-0.79

 predictive

-0.69

 observable

-0.66

 stakes

-0.66

close

-0.62

 abdom

-0.62

 messy

-0.61

 mischief

-0.61

lict

-0.60

POSITIVE LOGITS

Kam

1.03

aran

0.94

imura

0.94

ita

0.93

ata

0.90

 Chun

0.89

stead

0.87

akura

0.85

atsu

0.84

ara

0.83

Activations Density 0.008%

instances of the word "Kam" followed by a numerical value of 9 or 10

occurrences of the name "Kam" and its variations in context

No Comments

No Known Activations