INDEX

Explanations

references to "block" types and their associated properties or counts

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

%)$

-0.79

stdarg

-0.75

Ory

-0.74

 vatt

-0.73

 Keating

-0.72

RNN

-0.72

 للاسماء

-0.72

 cheiro

-0.70

HttpFoundation

-0.70

zczegól

-0.70

POSITIVE LOGITS

 block

2.53

 BLOCK

2.52

 Block

2.50

block

2.46

 blocks

2.44

Block

2.33

BLOCK

2.32

 Blocks

2.27

blocks

2.23

Blocks

2.07

Activations Density 0.058%

references to "block" types and their associated properties or counts

No Comments

No Known Activations