INDEX

Explanations

the verb "discovered."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "discover" or its variations

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

req

-0.74

gage

-0.72

VP

-0.71

respective

-0.70

Ã±a

-0.69

ranged

-0.69

cour

-0.67

wrap

-0.66

quote

-0.64

quet

-0.64

POSITIVE LOGITS

 flaws

0.85

 anew

0.85

 unsus

0.83

 truths

0.82

ibility

0.78

 firsthand

0.78

 treasures

0.73

 ways

0.71

ibly

0.71

 inconsistencies

0.70

Activations Density 0.054%

the verb "discovered."

occurrences of the word "discover" or its variations

No Comments

No Known Activations