INDEX

Explanations

occurrences of logical values and conditions in programming or data handling contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

EndInit

-0.59

 parseFrom

-0.58

 AssemblyProduct

-0.58

BeginInit

-0.48

↘

-0.48

IndentedString

-0.47

Overlap

-0.47

styleable

-0.47

TagMode

-0.47

 postIndex

-0.46

POSITIVE LOGITS

 null

0.94

DBNull

0.94

 blank

0.92

 Null

0.92

NaN

0.92

 DBNull

0.91

Null

0.90

 missing

0.88

NaN

0.87

 undefined

0.80

Activations Density 0.497%

occurrences of logical values and conditions in programming or data handling contexts

No Comments

No Known Activations