INDEX

Explanations

phrases related to consequences or outcomes

oai_token-act-pair · gpt-3.5-turbo

instances of dependent clauses or phrases that introduce additional information

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

OND

-0.74

RP

-0.68

rack

-0.68

SON

-0.67

soDeliveryDate

-0.67

SB

-0.66

orn

-0.66

oph

-0.64

worth

-0.64

Sync

-0.63

POSITIVE LOGITS

 however

1.08

 meanwhile

0.81

 moreover

0.80

 though

0.75

 please

0.69

 Canaver

0.66

 disse

0.65

 which

0.65

 wherein

0.65

 albeit

0.63

Activations Density 0.527%

phrases related to consequences or outcomes

instances of dependent clauses or phrases that introduce additional information

No Comments

No Known Activations