INDEX

Explanations

contextual elements and key components related to personal or professional conflicts and interactions

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

>*/

-0.62

 ModelExpression

-0.58

SequentialGroup

-0.57

 typelib

-0.56

finch

-0.54

̍t

-0.54

 vermelha

-0.54

 händer

-0.53

 toscana

-0.52

 solides

-0.52

POSITIVE LOGITS

CopyWith

0.57

 sendiri

0.56

Portale

0.55

neg

0.52

offsetof

0.52

ſelf

0.52

 clearColor

0.51

tidine

0.51

glEnd

0.51

andExpect

0.51

Activations Density 0.308%

contextual elements and key components related to personal or professional conflicts and interactions

No Comments

No Known Activations