INDEX

Explanations

references to specific locations and individuals, particularly in the context of legal or historical discussions

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

 Calla

-0.74

 Witten

-0.74

 Johnnie

-0.70

 Flanagan

-0.69

Retain

-0.68

Fris

-0.68

 fris

-0.67

Kue

-0.67

 astron

-0.66

 Scherer

-0.66

POSITIVE LOGITS

SqlParameter

1.04

.*")]

0.89

endphp

0.84

djangoproject

0.82

CodeAnalysis

0.82

AddTagHelper

0.80

Pittsburgh

0.80

kafka

0.80

endpush

0.79

JdbcTemplate

0.78

Activations Density 2.714%

references to specific locations and individuals, particularly in the context of legal or historical discussions

No Comments

No Known Activations