INDEX

Explanations

headers and specific formatting cues in texts related to technical and medical documentation

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

 transfieras

-0.69

expandindo

-0.67

@"/

-0.67

uxxxx

-0.66

 maux

-0.65

AddTagHelper

-0.65

Искәрмәләр

-0.64

 Reihe

-0.63

GeneratedMessage

-0.62

ạch

-0.62

POSITIVE LOGITS

 view

0.77

 VIEW

0.71

 View

0.66

Demografia

0.66

 views

0.65

VIEW

0.61

 VIEWS

0.60

 getView

0.60

viewtopic

0.58

viewType

0.58

Activations Density 0.051%

headers and specific formatting cues in texts related to technical and medical documentation

No Comments

No Known Activations