INDEX

Explanations

phrases related to a series of events or occurrences

oai_token-act-pair · gpt-3.5-turbo

the phrase "a series of" indicating a collection or sequence of items or events

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

uca

-0.80

vale

-0.72

ability

-0.70

YA

-0.68

arers

-0.68

adelphia

-0.67

VO

-0.66

rament

-0.65

KEN

-0.64

hester

-0.64

POSITIVE LOGITS

 events

0.83

 reforms

0.76

 successive

0.76

 articles

0.76

 episodes

0.74

 headlines

0.73

 alternating

0.72

 consecutive

0.71

 releases

0.70

 setbacks

0.69

Activations Density 0.074%

phrases related to a series of events or occurrences

the phrase "a series of" indicating a collection or sequence of items or events

No Comments

No Known Activations