INDEX

Explanations

questioning statements in a conversation

oai_token-act-pair · gpt-3.5-turbo

expressions indicating doubt or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 approximate

-0.73

 glean

-0.71

 sleeve

-0.69

 vaguely

-0.69

 earliest

-0.68

 pecul

-0.67

Registered

-0.67

 tooltip

-0.66

 similarities

-0.63

 cler

-0.61

POSITIVE LOGITS

nor

1.30

 anymore

1.17

nor

1.09

unless

1.09

 Especially

0.97

:(

0.94

 unless

0.89

 Therefore

0.88

yet

0.85

Therefore

0.85

Activations Density 0.581%

questioning statements in a conversation

expressions indicating doubt or uncertainty

No Comments

No Known Activations