INDEX

Explanations

positive outcomes or achievements

oai_token-act-pair · gpt-3.5-turbo

indicators of success or failure 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 @ 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

 excessively

-0.63

XY

-0.61

 brightly

-0.59

noxious

-0.57

 fancy

-0.54

 deadliest

-0.53

 nifty

-0.51

 plainly

-0.51

 cultured

-0.51

 Butcher

-0.50

POSITIVE LOGITS

abal

0.68

arial

0.68

onis

0.65

SHIP

0.65

ologies

0.63

iations

0.61

ibilities

0.60

0.59

WARE

0.59

ings

0.59

Activations Density 0.746%

positive outcomes or achievements

indicators of success or failure in various contexts

No Comments

No Known Activations