INDEX

Explanations

confessions or admissions

oai_token-act-pair · gpt-3.5-turbo

phrases that include the verb "admit" and its related forms

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

soDeliveryDate

-0.70

 gears

-0.67

 enlarge

-0.63

patch

-0.63

////////////////////////////////

-0.62

_-

-0.61

 folders

-0.61

EDIT

-0.61

 lantern

-0.61

kb

-0.60

POSITIVE LOGITS

 wrongdoing

0.85

 innocence

0.77

 unres

0.69

incerity

0.68

 faked

0.67

aram

0.67

 complicity

0.66

peria

0.66

rosso

0.64

 authenticity

0.63

Activations Density 0.151%

confessions or admissions

phrases that include the verb "admit" and its related forms

No Comments

No Known Activations