INDEX

Explanations

various mentions of the word "selection", both simple and in specific contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "selection."

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

peria

-0.77

kos

-0.76

wig

-0.72

mond

-0.67

pton

-0.65

hur

-0.64

alone

-0.63

FORMATION

-0.61

ned

-0.61

aths

-0.61

POSITIVE LOGITS

selection

1.13

 criteria

0.91

 selection

0.88

 Selection

0.84

ivity

0.82

 selections

0.81

eering

0.79

axe

0.78

azy

0.77

ively

0.76

Activations Density 0.021%

various mentions of the word "selection", both simple and in specific contexts

instances of the word "selection."

No Comments

No Known Activations