INDEX

Explanations

mentions of the term "Atlas"

oai_token-act-pair · gpt-3.5-turbo

mentions of the "Atlas" rocket and related 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

stakes

-0.75

adows

-0.72

adow

-0.69

 Bride

-0.69

dt

-0.65

ODUCT

-0.64

igrants

-0.63

uci

-0.62

isance

-0.62

 Pearce

-0.61

POSITIVE LOGITS

omach

0.98

©¶æ¥µ

0.78

cles

0.70

Corp

0.68

wegian

0.65

 choke

0.65

 Carnegie

0.65

rian

0.64

 Dynam

0.64

Mobil

0.63

Activations Density 0.031%

mentions of the term "Atlas"

mentions of the "Atlas" rocket and related contexts

No Comments

No Known Activations