INDEX

Explanations

mentions of specific entities or names, possibly related to politics or current events

oai_token-act-pair · gpt-3.5-turbo

specific names and terms related to political and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Thumbnail

-0.70

ume

-0.65

 Nanto

-0.63

!--

-0.60

Synopsis

-0.59

 mascul

-0.59

andise

-0.58

 imagin

-0.58

udo

-0.57

 ....

-0.57

POSITIVE LOGITS

helps

0.68

bay

0.67

 hadn

0.66

osaurs

0.66

bably

0.66

cheat

0.66

 existed

0.64

 shouldn

0.64

 deserved

0.64

 exists

0.63

Activations Density 0.658%

mentions of specific entities or names, possibly related to politics or current events

specific names and terms related to political and societal issues

No Comments

No Known Activations