INDEX

Explanations

the word "ben" with different numeric activations

oai_token-act-pair · gpt-3.5-turbo

the presence of the term "ben" in various contexts

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

 Kinnikuman

-0.83

WD

-0.66

inarily

-0.65

RS

-0.64

mson

-0.64

earable

-0.62

displayText

-0.61

matic

-0.60

CV

-0.60

TPPStreamerBot

-0.58

POSITIVE LOGITS

jamin

1.62

ghazi

0.97

furt

0.92

nington

0.89

chers

0.88

cher

0.85

heimer

0.84

acon

0.83

emies

0.82

ben

0.81

Activations Density 0.015%

the word "ben" with different numeric activations

the presence of the term "ben" in various contexts

No Comments

No Known Activations