INDEX

Explanations

the word "until" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Bronnen

-0.72

ICH

-0.71

opa

-0.71

LPS

-0.70

 Agus

-0.70

 alha

-0.70

 Pompey

-0.70

 Jonah

-0.69

%)$

-0.68

SRS

-0.67

POSITIVE LOGITS

 until

1.79

 UNTIL

1.74

until

1.69

 untill

1.67

 Until

1.65

Until

1.64

 till

1.61

 TILL

1.54

 Till

1.45

Till

1.44

Activations Density 0.064%

the word "until" in various contexts

No Comments

No Known Activations