INDEX

Explanations

code snippets involving conditional statements and media type handling in web applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Says

-0.79

styleable

-0.70

Adds

-0.69

 Holds

-0.69

 Says

-0.69

 SAYS

-0.66

 Gives

-0.66

Continues

-0.65

Bringing

-0.64

 Describes

-0.63

POSITIVE LOGITS

 requested

0.86

 offered

0.84

 submitted

0.83

 returned

0.82

 entered

0.81

 appealed

0.79

 demanded

0.79

 analysed

0.76

 contacted

0.76

 interpreted

0.76

Activations Density 0.371%

code snippets involving conditional statements and media type handling in web applications

No Comments

No Known Activations