INDEX

Explanations

phrases indicating the need for further investigation or research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

migrationBuilder

-0.64

TagHelper

-0.61

AddTagHelper

-0.61

RegressionTest

-0.58

GeoNames

-0.57

]}>

-0.55

]));

-0.54

SequentialGroup

-0.53

TabIndex

-0.53

ftagPool

-0.53

POSITIVE LOGITS

 whether

0.62

cra

0.56

 conclusive

0.53

PROBE

0.53

 unknow

0.52

 uncertain

0.49

 pois

0.49

 undetermined

0.48

 gespannt

0.47

 ransom

0.47

Activations Density 0.627%

phrases indicating the need for further investigation or research

No Comments

No Known Activations