INDEX

Explanations

references to the term "Star"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Star" 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 attribution

-0.75

 disse

-0.73

 landsl

-0.71

 defe

-0.69

ktop

-0.68

GV

-0.68

 upstream

-0.67

 downstream

-0.66

 suscept

-0.66

mits

-0.66

POSITIVE LOGITS

 Star

3.65

Star

2.78

 STAR

2.46

star

2.22

 Stars

2.04

STAR

1.75

 star

1.73

Stars

1.70

stars

1.58

 Stard

1.55

Activations Density 0.011%

references to the term "Star"

occurrences of the word "Star" in various contexts

No Comments

No Known Activations