INDEX

Explanations

unexpected or surprising elements within a narrative

oai_token-act-pair · gpt-3.5-turbo

phrases indicating new developments or significant changes in circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arer

-0.71

 Unloaded

-0.70

hner

-0.69

inventoryQuantity

-0.68

urated

-0.67

hovah

-0.66

arus

-0.66

hement

-0.64

addons

-0.64

 Indies

-0.63

POSITIVE LOGITS

:,

0.87

0.86

:]

0.86

 namely

0.80

:#

0.77

]:

0.76

%:

0.76

():

0.75

:[

0.74

!:

0.73

Activations Density 0.375%

unexpected or surprising elements within a narrative

phrases indicating new developments or significant changes in circumstances

No Comments

No Known Activations