INDEX

Explanations

phrases related to decision-making and choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

JsonIgnore

-0.64

ValueStyle

-0.59

NameInMap

-0.57

 stellte

-0.57

országban

-0.55

posites

-0.53

 оригіналу

-0.52

født

-0.52

ViewFeatures

-0.51

$}}

-0.51

POSITIVE LOGITS

 should

0.80

 appropriate

0.76

 future

0.75

 Should

0.74

 desired

0.72

should

0.68

 suitable

0.68

Should

0.68

要不要

0.68

 fate

0.67

Activations Density 0.423%

phrases related to decision-making and choices

No Comments

No Known Activations