INDEX

Explanations

locations or venues in sports events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "at" in various contexts

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

FTWARE

-0.68

itarian

-0.68

aceutical

-0.62

alpha

-0.62

 Employees

-0.61

photo

-0.61

INESS

-0.61

idav

-0.61

 Customers

-0.60

erness

-0.60

POSITIVE LOGITS

 halftime

1.21

 least

1.06

 midfield

0.86

 fullback

0.86

 home

0.86

las

0.85

 Wembley

0.84

onement

0.82

letico

0.81

 variance

0.80

Activations Density 0.119%

locations or venues in sports events

occurrences of the word "at" in various contexts

No Comments

No Known Activations