INDEX

Explanations

numerical data and sequences

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

onViewCreated

-1.09

findpost

-0.99

 فريبيس

-0.98

onAttach

-0.98



-0.95

 MonoBehaviour

-0.90

Hochspringen

-0.85

 يتيمه

-0.82

 '\\;'

-0.82

ScopeManager

-0.81

POSITIVE LOGITS

0.58

0.57

ivan

0.49

 actual

0.47

 best

0.47

aldas

0.46

ssa

0.46

ilu

0.45

Activations Density 0.932%

numerical data and sequences

No Comments

No Known Activations