INDEX

Explanations

terms related to joining or affiliation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

aeus

-0.75

worn

-0.74

each

-0.72

handedly

-0.72

 resorted

-0.71

fulness

-0.71

 namely

-0.66

rand

-0.66

 relating

-0.64

.-

-0.63

POSITIVE LOGITS

 fray

1.60

 ranks

1.09

 same

0.96

 chorus

0.88

 broader

0.86

 confines

0.84

 latest

0.84

 realm

0.84

 wider

0.83

 forefront

0.83

Activations Density 0.231%

terms related to joining or affiliation

instances of the word "the"

No Comments

No Known Activations