INDEX

Explanations

references to "chains" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-0.92

//};

-0.88

uſ

-0.86

 uſed

-0.83

 réfugi

-0.82

()]);

-0.81

 deſt

-0.81

 intersti

-0.81

 themſelves

-0.80

 ſmall

-0.80

POSITIVE LOGITS

 chains

1.92

 chain

1.89

 Chains

1.72

 Chain

1.66

 CHAIN

1.64

chains

1.64

chain

1.60

Chain

1.49

Chains

1.48

CHAIN

1.41

Activations Density 0.076%

references to "chains" in various contexts

No Comments

No Known Activations