INDEX

Explanations

different variations of the term "BL" with decreasing activations

oai_token-act-pair · gpt-3.5-turbo

references to a specific television or media series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

enegger

-0.84

mble

-0.81

framework

-0.76

aeda

-0.75

tainment

-0.73

gerald

-0.73

geist

-0.69

duc

-0.68

mens

-0.67

 Gund

-0.67

POSITIVE LOGITS

ACK

1.01

OOD

1.00

adder

0.96

ighting

0.96

anca

0.96

anche

0.93

OCK

0.91

umenthal

0.89

ADE

0.86

AST

0.85

Activations Density 0.008%

different variations of the term "BL" with decreasing activations

references to a specific television or media series

No Comments

No Known Activations