INDEX

Explanations

words related to operations or functioning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "operate" and its variants

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

hus

-0.73

hon

-0.73

ildo

-0.72

grave

-0.69

 Upton

-0.68

 Shards

-0.67

ioxide

-0.65

plet

-0.65

ilde

-0.65

urd

-0.63

POSITIVE LOGITS

 independently

0.75

 withd

0.72

 concurrently

0.70

river

0.68

querade

0.68

 theat

0.68

 lawfully

0.67

aution

0.67

 licences

0.67

ATING

0.67

Activations Density 0.044%

words related to operations or functioning

instances of the word "operate" and its variants

No Comments

No Known Activations