INDEX

Explanations

specific numerical patterns within URLs or text strings

oai_token-act-pair · gpt-3.5-turbo

numerical data or statistics

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

anooga

-0.82

 DRAG

-0.70

ierrez

-0.69

INGTON

-0.69

aughs

-0.66

 Mayo

-0.64

 Beir

-0.63

uyomi

-0.62

 scrut

-0.62

 SHAR

-0.61

POSITIVE LOGITS

1.01

0.99

0.98

/)

0.98

bg

0.98

0.97

fc

0.96

Activations Density 0.092%

specific numerical patterns within URLs or text strings

numerical data or statistics

No Comments

No Known Activations