INDEX

Explanations

positive expressions or actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to significant changes or developments in various contexts

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

iru

-0.61

 laun

-0.59

inki

-0.55

Accessory

-0.54

vice

-0.53

cig

-0.53

MJ

-0.51

vg

-0.50

 Ambro

-0.49

article

-0.48

POSITIVE LOGITS

 lately

1.10

 since

0.91

 recently

0.71

since

0.70

 countless

0.67

 numerous

0.65

 previously

0.60

successfully

0.59

 successfully

0.58

 extensively

0.58

Activations Density 1.152%

positive expressions or actions

phrases related to significant changes or developments in various contexts

No Comments

No Known Activations