INDEX

Explanations

array declarations or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.82

-0.70

-0.69

-0.68

on

-0.67

-0.66

me

-0.65

-0.64

ti

-0.64

Ob

-0.63

POSITIVE LOGITS

[]

1.96

>[]

1.54

[].

1.46

|[]

1.39

[][]

1.32

][]

1.25

[],

1.22

[]=

1.22

[]

1.21

[]"

1.20

Activations Density 0.040%

array declarations or definitions

No Comments

No Known Activations