INDEX

Explanations

phrases related to human existence or characteristics

oai_token-act-pair · gpt-3.5-turbo

references to the concept of being human

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Els

-0.73

 Mines

-0.71

NRS

-0.70

éĹĺ

-0.70

 Passage

-0.64

ories

-0.63

 redundancy

-0.62

ICE

-0.62

yss

-0.62

 Deadly

-0.61

POSITIVE LOGITS

 alive

0.91

hood

0.81

who

0.81

 lived

0.81

 judged

0.79

 inhab

0.78

 born

0.76

 endowed

0.75

atos

0.74

 beings

0.74

Activations Density 0.030%

phrases related to human existence or characteristics

references to the concept of being human

No Comments

No Known Activations