INDEX

Explanations

studies or research findings

oai_token-act-pair · gpt-3.5-turbo

instances of the word "found" 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

nom

-0.62

 Bride

-0.60

 partic

-0.60

 concess

-0.59

externalActionCode

-0.59

 gate

-0.58

 alias

-0.58

EStreamFrame

-0.57

commit

-0.57

via

-0.57

POSITIVE LOGITS

-+-+

0.76

oley

0.74

oots

0.71

itutional

0.70

uments

0.69

iveness

0.69

usky

0.68

eele

0.67

Leaks

0.67

ries

0.67

Activations Density 0.050%

studies or research findings

instances of the word "found" in various contexts

No Comments

No Known Activations