INDEX

Explanations

phrases indicating a change in topic or a transition in a conversation

oai_token-act-pair · gpt-3.5-turbo

the word "anyway" and its variations, indicating a shift in conversation or topic

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

 solitary

-0.69

prus

-0.65

 brig

-0.63

 prost

-0.63

adr

-0.62

©¶æ

-0.60

urg

-0.59

 crucifix

-0.58

 centerpiece

-0.56

negie

-0.55

POSITIVE LOGITS

 Anyway

0.94

 anyways

0.89

ional

0.83

 anyway

0.82

Anyway

0.80

 gotta

0.75

forth

0.74

ipop

0.74

hey

0.73

leep

0.73

Activations Density 0.022%

phrases indicating a change in topic or a transition in a conversation

the word "anyway" and its variations, indicating a shift in conversation or topic

No Comments

No Known Activations