INDEX

Explanations

phrases indicating a future event

oai_token-act-pair · gpt-3.5-turbo

phrases indicating future events or actions that are planned or anticipated

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Sense

-0.64

luence

-0.64

paste

-0.63

loo

-0.61

illian

-0.61

issance

-0.60

ory

-0.56

ocation

-0.55

inventoryQuantity

-0.54

older

-0.54

POSITIVE LOGITS

tle

1.13

 forth

0.91

ters

0.91

 aside

0.89

upt

0.88

ter

0.87

abl

0.86

 sail

0.82

tering

0.82

tered

0.82

Activations Density 0.038%

phrases indicating a future event

phrases indicating future events or actions that are planned or anticipated

No Comments

No Known Activations