INDEX

Explanations

action verbs related to procedures or processes

oai_token-act-pair · gpt-3.5-turbo

verbs indicating the addition or calculation of data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inventoryQuantity

-0.71

humans

-0.69

vacc

-0.69

milo

-0.68

Fs

-0.65

ãĤ·

-0.63

Neg

-0.63

spir

-0.62

psc

-0.61

bara

-0.61

POSITIVE LOGITS

 separately

0.82

 automatically

0.79

 accordingly

0.75

 periodically

0.71

by

0.69

 randomly

0.68

oven

0.67

itored

0.67

 individually

0.66

ynamic

0.65

Activations Density 0.247%

action verbs related to procedures or processes

verbs indicating the addition or calculation of data

No Comments

No Known Activations