INDEX

Explanations

relationships and causal links in data-driven contexts

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

läg

-0.52

 OMIT

-0.52

setLong

-0.49

fören

-0.48

 TestBed

-0.46

 avsl

-0.46

ExecuteReader

-0.45

rätt

-0.45

 olvides

-0.44

こん

-0.44

POSITIVE LOGITS

PreferredItem

0.77

AddTagHelper

0.72

Élet

0.62

集中

0.61

▻

0.60

IsContent

0.60

íncia

0.60

 '\\;'

0.59

centiles

0.58

 primarily

0.58

Activations Density 0.529%

relationships and causal links in data-driven contexts

No Comments

No Known Activations