INDEX

Explanations

words related to the act of entering

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "entering."

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

andra

-0.67

anan

-0.66

apes

-0.65

bara

-0.62

urd

-0.62

idy

-0.60

pdf

-0.57

erb

-0.56

Rep

-0.56

ublic

-0.56

POSITIVE LOGITS

 entering

3.39

 exiting

1.88

 enter

1.85

 entered

1.76

 heading

1.61

 enters

1.60

 arriving

1.58

 accessing

1.55

 encountering

1.42

 joining

1.41

Activations Density 0.010%

words related to the act of entering

occurrences of the word "entering."

No Comments

No Known Activations