INDEX

Explanations

statements about potentially controversial or misleading medical claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

</tfoot>

-0.77

 виправивши

-0.77

 Theſe

-0.68

tvguidetime

-0.67

Efq

-0.66

 Anſ

-0.66

 theſe

-0.66

Tikang

-0.66

 TextInputType

-0.65

 BorderSide

-0.64

POSITIVE LOGITS

Personendaten

0.65

 seien

0.58

parsedMessage

0.57

MessageTagHelper

0.55

 noting

0.52

writeFieldEnd

0.51

 said

0.50

said

0.50

 señaló

0.49

 udaler

0.49

Activations Density 0.387%

statements about potentially controversial or misleading medical claims

No Comments

No Known Activations