INDEX

Explanations

instances where the word "too" is used to show addition or agreement with a previous statement

oai_token-act-pair · gpt-3.5-turbo

the word "too" in various contexts, indicating excess or addition

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

icipated

-0.64

 Hammond

-0.60

inity

-0.60

 plurality

-0.58

inarily

-0.58

idia

-0.58

 impossibility

-0.58

 takedown

-0.56

 Hearts

-0.56

cu

-0.55

POSITIVE LOGITS

:)

0.83

oths

0.80

 much

0.78

 guiActiveUn

0.76

;)

0.74

ille

0.74

.,

0.73

:-)

0.73

far

0.73

!.

0.72

Activations Density 0.029%

instances where the word "too" is used to show addition or agreement with a previous statement

the word "too" in various contexts, indicating excess or addition

No Comments

No Known Activations