INDEX

Explanations

phrases related to specific people or personal experiences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

 thereby

-0.83

 according

-0.81

âĢł

-0.78

 alongside

-0.68

 jointly

-0.67

 based

-0.66

 overseen

-0.66

Malley

-0.66

 authored

-0.64

buster

-0.64

POSITIVE LOGITS

 slightest

1.26

 whole

1.12

 smallest

1.11

 hardest

1.09

 simplest

1.09

 easiest

1.06

 biggest

1.04

 brightest

1.02

 coolest

1.00

 longest

0.99

Activations Density 1.079%

phrases related to specific people or personal experiences

occurrences of the word "the."

No Comments

No Known Activations