INDEX

Explanations

sentences related to performance evaluations

oai_token-act-pair · gpt-3.5-turbo

conclusive statements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 clandestine

-0.84

 hijacked

-0.83

 unsuspecting

-0.81

 authorized

-0.76

 authorised

-0.75

agen

-0.75

ricanes

-0.75

 malfunction

-0.74

 tricked

-0.74

 innocuous

-0.73

POSITIVE LOGITS

 Lastly

1.51

 Additionally

1.45

 Also

1.43

 Highly

1.43

 Plus

1.42

 Definitely

1.40

 Furthermore

1.40

 Overall

1.38

 Moreover

1.37

 Especially

1.37

Activations Density 0.396%

sentences related to performance evaluations

conclusive statements or observations

No Comments

No Known Activations