INDEX

Explanations

the presence of sentences or statements, particularly focusing on periods as sentence delimiters

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

 himſelf

-0.93

 itſelf

-0.92

 myſelf

-0.90

 leaſt

-0.88

 ſever

-0.85

 iſt

-0.84

 fevere

-0.83

 faſt

-0.82

 pleaſure

-0.82

 poffe

-0.82

POSITIVE LOGITS

0.99

0.76

\.

0.68

{.

0.65

//.

0.60

<eos>

0.58

_.

0.57

&.

0.55

?.

0.53

().

0.53

Activations Density 0.171%

the presence of sentences or statements, particularly focusing on periods as sentence delimiters

No Comments

No Known Activations