INDEX

Explanations

instances where someone expresses doubt or correction about something

oai_token-act-pair · gpt-3.5-turbo

the word "about" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

hesis

-0.90

rang

-0.77

 Peaks

-0.75

KC

-0.74

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.71

hai

-0.70

hiba

-0.70

ammy

-0.68

âķĲâķĲ

-0.67

hetical

-0.66

POSITIVE LOGITS

how

0.77

 respecting

0.76

 whether

0.74

 halfway

0.74

 donating

0.71

 vaccines

0.71

 vaccinations

0.70

 quitting

0.69

 trusting

0.68

 accepting

0.68

Activations Density 0.101%

instances where someone expresses doubt or correction about something

the word "about" in various contexts

No Comments

No Known Activations