INDEX

Explanations

phrases related to various scenes or communities

oai_token-act-pair · gpt-3.5-turbo

references to various "scenes" across different cultural 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

 Gund

-0.75

thood

-0.71

heit

-0.70

ippi

-0.66

icrobial

-0.65

Ã£

-0.64

endars

-0.64

oug

-0.64

ono

-0.63

milo

-0.62

POSITIVE LOGITS

LINE

0.86

osphere

0.82

Quote

0.69

Capture

0.69

>>>>>>>>

0.68

Dialogue

0.68

ologist

0.68

Oracle

0.67

 Scene

0.67

scene

0.65

Activations Density 0.016%

phrases related to various scenes or communities

references to various "scenes" across different cultural contexts

No Comments

No Known Activations