INDEX

Explanations

expressions indicating expectations or comparisons in sentiment

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

+#+

-0.75

MessageTagHelper

-0.74

ContentAsync

-0.67

 NSCoder

-0.67

 Wiktionnaire

-0.61

ukunft

-0.61

Secondo

-0.58

tvguidetime

-0.57

glBindTexture

-0.57

jelder

-0.56

POSITIVE LOGITS

 anticipated

0.84

 originally

0.78

 initially

0.77

 hoped

0.76

 imagined

0.75

 expected

0.69

 envisioned

0.66

 indicated

0.63

 intended

0.61

Originally

0.60

Activations Density 0.162%

expressions indicating expectations or comparisons in sentiment

No Comments

No Known Activations