INDEX

Explanations

phrases relating to making assumptions or hypotheses

oai_token-act-pair · gpt-3.5-turbo

instances of the word "assuming" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Rated

-0.78

nels

-0.78

cart

-0.73

emetery

-0.73

 Canyon

-0.73

Quality

-0.70

tr

-0.69

âĵĺ

-0.69

taboola

-0.69

ng

-0.68

POSITIVE LOGITS

 assuming

0.90

 assum

0.79

heon

0.78

utical

0.77

 assume

0.74

 Lauder

0.71

 presume

0.70

inet

0.68

iture

0.68

 presum

0.68

Activations Density 0.010%

phrases relating to making assumptions or hypotheses

instances of the word "assuming" in various contexts

No Comments

No Known Activations