INDEX

Explanations

words related to publication or being published

oai_token-act-pair · gpt-3.5-turbo

instances of the word "published" and its variations in different 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

llan

-0.89

phant

-0.75

 awakened

-0.71

xa

-0.70

nea

-0.69

bones

-0.69

enhagen

-0.68

ichael

-0.68

uppet

-0.67

ugh

-0.67

POSITIVE LOGITS

lishing

1.12

lisher

1.06

 excerpts

0.99

lishes

0.83

 exploits

0.74

 Journals

0.73

 articles

0.72

 publication

0.72

 transcripts

0.70

ulations

0.69

Activations Density 0.051%

words related to publication or being published

instances of the word "published" and its variations in different contexts

No Comments

No Known Activations