INDEX

Explanations

dates or events within text

oai_token-act-pair · gpt-3.5-turbo

emotional expressions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.88

 favour

-0.85

 disciplines

-0.84

 edged

-0.83

 governed

-0.82

 accelerator

-0.79

 regener

-0.79

 persu

-0.79

 commissions

-0.77

 greenhouse

-0.77

POSITIVE LOGITS

Looks

1.66

RIP

1.65

1.64

Others

1.56

Wow

1.56

Cong

1.55

https

1.55

Advertisements

1.54

BRE

1.50

Apparently

1.49

Activations Density 0.201%

dates or events within text

emotional expressions or sentiments

No Comments

No Known Activations