INDEX

Explanations

companies, institutions, or individuals mentioned in a list

oai_token-act-pair · gpt-3.5-turbo

references to collective entities or movements in technology and popular culture

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

afety

-0.71

bow

-0.66

 Woodward

-0.66

)]

-0.65

iquette

-0.63

 Correction

-0.62

":"/

-0.61

 Lavrov

-0.59

 correction

-0.59

nosis

-0.58

POSITIVE LOGITS

 respectively

1.49

 combined

0.91

 latter

0.86

pta

0.77

 collectively

0.76

together

0.74

 jointly

0.72

etc

0.71

 culminated

0.69

 variations

0.69

Activations Density 1.082%

companies, institutions, or individuals mentioned in a list

references to collective entities or movements in technology and popular culture

No Comments

No Known Activations