INDEX

Explanations

complex words with a prefix 'double-' followed by another set of characters

oai_token-act-pair · gpt-3.5-turbo

phrases related to double meanings or dual interpretations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

SPONSORED

-0.68

 uncond

-0.66

 Maher

-0.62

 Weak

-0.62

 Pool

-0.61

uddin

-0.58

 Survivor

-0.58

USL

-0.58

urga

-0.57

RAW

-0.57

POSITIVE LOGITS

ammy

0.99

Unix

0.76

alion

0.75

imeters

0.75

acters

0.74

rencies

0.73

tein

0.73

agos

0.71

fect

0.68

äºĶ

0.68

Activations Density 0.096%

complex words with a prefix 'double-' followed by another set of characters

phrases related to double meanings or dual interpretations

No Comments

No Known Activations