INDEX

Explanations

occurrences of the word "email" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 htons

-0.79

('--

-0.73

 stanovnika

-0.71

stan

-0.70

']>

-0.70

 createSprite

-0.70

WebVitals

-0.69

GTS

-0.69

 Roskov

-0.68

 offensively

-0.68

POSITIVE LOGITS

 email

1.91

Email

1.84

 EMAIL

1.84

 emails

1.82

 Email

1.81

 getEmail

1.78

EMAIL

1.77

email

1.68

Emails

1.66

getEmail

1.64

Activations Density 0.029%

occurrences of the word "email" in various contexts

No Comments

No Known Activations