INDEX

Explanations

formatted string literals or escape sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 يتيمه

-0.93

ICS

-0.82

 Gass

-0.80

########.

-0.78

mybatisplus

-0.76

 Langford

-0.73

ghost

-0.72

 ghost

-0.72

 Idaho

-0.70

 Mombasa

-0.69

POSITIVE LOGITS

("\

1.93

('\

1.81

"\

1.80

"\

1.76

,"\

1.63

="\

1.60

<<"\

1.59

'\

1.55

,'\

1.55

'\

1.50

Activations Density 0.302%

formatted string literals or escape sequences

No Comments

No Known Activations