INDEX

Explanations

phrases indicating spatial location

oai_token-act-pair · gpt-3.5-turbo

references to positions in a structured list, such as rankings or placements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

arily

-0.86

-0.74

Äĩ

-0.72

 reperto

-0.71

dayName

-0.71

terday

-0.69

wcs

-0.68

Ô

-0.68

>>>>>>>>

-0.68

 Cosponsors

-0.68

POSITIVE LOGITS

 Buckingham

0.71

 Entry

0.68

 each

0.67

 Tennessee

0.67

 Sutherland

0.67

gall

0.66

loaded

0.64

 Gillespie

0.63

 Appalach

0.63

 course

0.63

Activations Density 0.116%

phrases indicating spatial location

references to positions in a structured list, such as rankings or placements

No Comments

No Known Activations