INDEX

Explanations

references to chains or sequences, particularly in a context of causes and effects or connections

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.92

 juſt

-0.92

uſ

-0.87

 deſt

-0.85

PhysRevD

-0.83

//};

-0.82

vados

-0.82

 intersti

-0.81

 obſ

-0.81

 Cabrio

-0.81

POSITIVE LOGITS

 chain

2.61

 chains

2.46

 Chain

2.26

chain

2.25

 CHAIN

2.19

Chain

2.12

 Chains

2.10

chains

2.04

Chains

1.91

CHAIN

1.84

Activations Density 0.058%

references to chains or sequences, particularly in a context of causes and effects or connections

No Comments

No Known Activations