INDEX

Explanations

references to administrative processes or systems

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "administrative" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ï¸

-0.85

enegger

-0.84

âķĲâķĲ

-0.84

pheus

-0.80

Temperature

-0.78

DonaldTrump

-0.78

ï¸ı

-0.74

 Temper

-0.74

 Chrom

-0.72

 Emin

-0.71

POSITIVE LOGITS

rative

1.05

stration

1.01

istration

0.94

 administ

0.87

 administrative

0.86

uthor

0.85

 administrator

0.83

 princip

0.82

administ

0.79

istry

0.78

Activations Density 0.026%

references to administrative processes or systems

occurrences of the term "administrative" and related concepts

No Comments

No Known Activations