INDEX

Explanations

words related to prompting actions or reactions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "prompt" 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 @ 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

à©

-0.68

aird

-0.65

 Leaves

-0.63

ihar

-0.60

 Corpse

-0.60

rend

-0.59

 cannabinoid

-0.59

 Cortex

-0.59

 Vaughan

-0.58

 fung

-0.58

POSITIVE LOGITS

 prompt

1.12

 prompts

1.00

 prompting

0.88

iration

0.87

 prompted

0.80

ienced

0.80

 inquiries

0.79

rising

0.78

 showc

0.77

ously

0.77

Activations Density 0.018%

words related to prompting actions or reactions

instances of the word "prompt" and its variations in context

No Comments

No Known Activations