INDEX

Explanations

verbs related to providing explanations or reasons

oai_token-act-pair · gpt-3.5-turbo

instances of the word "explain" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

illet

-0.81

engeance

-0.80

estial

-0.73

thritis

-0.71

nown

-0.71

inal

-0.71

ortunately

-0.69

mire

-0.67

atri

-0.67

 pione

-0.66

POSITIVE LOGITS

why

1.13

WHY

1.12

 explain

1.06

why

1.01

 explanations

1.01

 explains

1.01

 Explain

0.99

 explan

0.96

 explaining

0.93

cases

0.92

Activations Density 0.019%

verbs related to providing explanations or reasons

instances of the word "explain" in various contexts

No Comments

No Known Activations