INDEX

Explanations

words related to operation or functioning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "operate" and its variations 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

-0.74

ixed

-0.71

hon

-0.70

iami

-0.68

von

-0.68

panic

-0.68

lake

-0.65

oning

-0.65

ildo

-0.65

alon

-0.64

POSITIVE LOGITS

 operated

0.81

 withd

0.75

aution

0.74

 operations

0.72

rative

0.70

 licences

0.70

atives

0.70

 operating

0.69

 ration

0.67

ational

0.67

Activations Density 0.020%

words related to operation or functioning

instances of the word "operate" and its variations in various contexts

No Comments

No Known Activations