INDEX

Explanations

references to actions or events based on reports or claims by others

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ooth

-0.72

apon

-0.71

ãĥĺ

-0.69

soever

-0.68

hei

-0.68

 listened

-0.67

acet

-0.65

adow

-0.65

anooga

-0.64

 because

-0.64

POSITIVE LOGITS

 latter

1.21

 latest

1.21

 aforementioned

1.08

 same

1.04

 Centers

0.94

 National

0.86

 Associated

0.86

 outset

0.85

 majority

0.84

 vast

0.83

Activations Density 0.144%

references to actions or events based on reports or claims by others

occurrences of the word "the" in various contexts

No Comments

No Known Activations