INDEX

Explanations

time-related phrases, particularly those indicating durations and sequences of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

mappedBy

-0.70

ngrx

-0.69

bestos

-0.60

WriteLiteral

-0.59

 springfox

-0.57

DebuggerNonUser

-0.56

AutoSize

-0.55

HtmlAttribute

-0.55

MCU

-0.55

bcryptjs

-0.54

POSITIVE LOGITS

 overnight

1.26

day

1.13

 weekend

1.08

 morning

1.04

vernight

0.99

day

0.99

DAY

0.99

 Overnight

0.96

 afternoon

0.96

Day

0.96

Activations Density 0.269%

time-related phrases, particularly those indicating durations and sequences of events

No Comments

No Known Activations