INDEX

Explanations

specific references to legal situations or individuals, particularly focusing on incidents involving Lester and related legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 ujednoznacz

-0.78

bart

-0.73

unzel

-0.70

an

-0.70

gung

-0.68

Vad

-0.67

Lif

-0.67

vad

-0.67

足

-0.67

ar

-0.66

POSITIVE LOGITS

 serpents

1.08

 Lester

0.97

RPS

0.96

 Esprit

0.95

TestingModule

0.94

 Reiss

0.93

 Cerr

0.93

TRS

0.91

srs

0.89

SRS

0.89

Activations Density 2.573%

specific references to legal situations or individuals, particularly focusing on incidents involving Lester and related legal terminology

No Comments

No Known Activations