INDEX

Explanations

various instances of the word "operate" in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "operate" and its variations

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

hus

-0.75

hon

-0.75

von

-0.72

ilde

-0.71

ixed

-0.69

alon

-0.67

xx

-0.67

binding

-0.67

 Upton

-0.66

username

-0.66

POSITIVE LOGITS

 withd

0.84

 operated

0.72

 operations

0.72

aution

0.71

querade

0.70

 operation

0.69

 flaw

0.68

abilities

0.68

 Procedure

0.67

ATING

0.66

Activations Density 0.032%

various instances of the word "operate" in different contexts

instances of the word "operate" and its variations

No Comments

No Known Activations