INDEX

Explanations

phrases related to family and various social issues or contexts where families are mentioned

oai_token-act-pair · gpt-3.5-turbo

references to families and their struggles or situations

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

Downloadha

-0.71

 Prom

-0.67

umbn

-0.64

 Hoover

-0.63

ðĿ

-0.63

ught

-0.63

 Flavoring

-0.62

REDACTED

-0.61

 Gaul

-0.61

rawdownloadcloneembedreportprint

-0.61

POSITIVE LOGITS

chool

1.08

folk

1.07

archs

0.77

ILY

0.74

heses

0.74

members

0.72

uci

0.71

hood

0.70

ilies

0.69

paces

0.69

Activations Density 0.022%

phrases related to family and various social issues or contexts where families are mentioned

references to families and their struggles or situations

No Comments

No Known Activations