INDEX

Explanations

terms related to data processing in batches

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

complexContent

-0.91

EDEFAULT

-0.86

 ModelRenderer

-0.80

 leetcode

-0.76

 mena

-0.76

aarrggbb

-0.75

ophon

-0.74

 ImageIcon

-0.71

WriteBarrier

-0.71

gameserver

-0.70

POSITIVE LOGITS

 batch

2.34

 Batch

2.17

batch

2.16

Batch

2.16

 BATCH

2.10

BATCH

2.00

 batches

1.93

batches

1.69

 lotes

1.35

 lote

1.34

Activations Density 0.083%

terms related to data processing in batches

No Comments

No Known Activations