INDEX

Explanations

mathematical symbols and expressions related to functions and sequences in a theoretical context

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

impri

-0.62

">//

-0.61

@",

-0.59

]>=

-0.59

 stable

-0.57

*)&

-0.56

()]

-0.55

 مرئيه

-0.55

ಞ

-0.55

])),

-0.55

POSITIVE LOGITS

dotenv

0.79

principalColumn

0.77

KURZBESCHREIBUNG

0.72

InjectAttribute

0.68

imageshack

0.66

enumi

0.66

AutoField

0.65

 vPvB

0.64

protoimpl

0.64

spender

0.63

Activations Density 1.562%

mathematical symbols and expressions related to functions and sequences in a theoretical context

No Comments

No Known Activations