INDEX

Explanations

phrases related to reflecting on or discussing various aspects of the term "pandering"

oai_token-act-pair · gpt-3.5-turbo

references to the word "panda" and its variants

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

 Lauder

-0.74

pell

-0.71

FUL

-0.64

shock

-0.64

fully

-0.63

 dstg

-0.63

terday

-0.63

 Eisen

-0.62

LECT

-0.58

 Jericho

-0.58

POSITIVE LOGITS

emonium

1.59

emic

1.45

ering

1.10

emonic

1.08

erers

1.06

elines

1.02

erest

0.96

aren

0.93

emon

0.93

ered

0.93

Activations Density 0.036%

phrases related to reflecting on or discussing various aspects of the term "pandering"

references to the word "panda" and its variants

No Comments

No Known Activations