INDEX

Explanations

statements related to political figures or officials from different organizations

oai_token-act-pair · gpt-3.5-turbo

prominent roles or titles 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

obin

-0.68

 unlucky

-0.62

OVER

-0.58

 lucky

-0.57

 hump

-0.57

rage

-0.57

oiler

-0.57

":"/

-0.56

OTUS

-0.55

 transformative

-0.54

POSITIVE LOGITS

0.77

 presided

0.69

 congratulated

0.68

accompanied

0.68

etc

0.67

appointed

0.64

 respectively

0.63

 Kard

0.63

pmwiki

0.62

udeb

0.62

Activations Density 0.417%

statements related to political figures or officials from different organizations

prominent roles or titles in various contexts

No Comments

No Known Activations