INDEX

Explanations

phrases relating to sports drafts or selections

oai_token-act-pair · gpt-3.5-turbo

references to draft picks in sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 interf

-0.80

english

-0.77

isf

-0.70

 lapt

-0.70

STD

-0.68

Sea

-0.67

igi

-0.67

hem

-0.66

ilit

-0.66

loo

-0.66

POSITIVE LOGITS

å£«

0.88

 Picks

0.86

 picks

0.84

pocket

0.83

axe

0.83

 pick

0.81

(#

0.78

Pick

0.77

opoulos

0.76

onom

0.73

Activations Density 0.025%

phrases relating to sports drafts or selections

references to draft picks in sports

No Comments

No Known Activations