INDEX

Explanations

references to utility functions and language-specific terms in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 mold

-0.63

copyFrom

-0.62

 Morph

-0.60

outez

-0.60

сылкі

-0.59

mold

-0.59

DataBinding

-0.58

Mold

-0.57

 Acha

-0.56

❷

-0.54

POSITIVE LOGITS

util

1.44

 util

1.13

Util

1.04

 Util

0.92

AxisAlignment

0.84

UTIL

0.77

 Utili

0.73

TagHelpers

0.73

 UTIL

0.69

uti

0.69

Activations Density 0.009%

references to utility functions and language-specific terms in programming contexts

No Comments

No Known Activations