INDEX

Explanations

references or citations within the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "reference" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

otos

-0.83

asus

-0.78

inho

-0.68

oly

-0.67

ihad

-0.66

ovation

-0.66

ãĥ£

-0.65

ssh

-0.64

keye

-0.64

wich

-0.64

POSITIVE LOGITS

 references

0.85

 counting

0.84

 therein

0.84

 thereto

0.82

ibly

0.73

 retrieved

0.73

 material

0.72

count

0.71

 citations

0.70

 numer

0.70

Activations Density 0.052%

references or citations within the text

occurrences of the word "reference" and its variations

No Comments

No Known Activations