INDEX

Explanations

words related to the abbreviation "Wo" followed by a numeric value

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word 'wo' and its variations

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

Magikarp

-0.87

ividual

-0.72

IUM

-0.71

 mileage

-0.70

 Uriel

-0.70

++++++++++++++++

-0.68

IONS

-0.67

âĸ¬

-0.67

REDACTED

-0.65

idates

-0.64

POSITIVE LOGITS

efully

1.14

ollen

1.11

ocom

1.09

eful

1.07

ofer

1.04

olly

1.01

ogie

0.95

asted

0.93

jo

0.93

wo

0.92

Activations Density 0.005%

words related to the abbreviation "Wo" followed by a numeric value

occurrences of the word 'wo' and its variations

No Comments

No Known Activations