INDEX

Explanations

phrases indicating a reason or justification for a particular action or situation

oai_token-act-pair · gpt-3.5-turbo

the phrase "given" frequently used 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inse

-0.83

addle

-0.76

cre

-0.70

ereo

-0.70

ierre

-0.69

star

-0.69

ipel

-0.68

imming

-0.68

queue

-0.68

jer

-0.67

POSITIVE LOGITS

 precedence

0.83

 precedent

0.83

 assurances

0.81

 circumstances

0.80

 ample

0.73

 indications

0.73

pend

0.71

 undue

0.69

 glimps

0.68

giving

0.67

Activations Density 0.027%

phrases indicating a reason or justification for a particular action or situation

the phrase "given" frequently used in various contexts

No Comments

No Known Activations