INDEX

Explanations

terms related to interviews or conversations

oai_token-act-pair · gpt-3.5-turbo

instances of strong 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 synerg

-0.78

 equival

-0.76

 cone

-0.76

pse

-0.75

 regenerate

-0.73

 undet

-0.73

 neglig

-0.73

 knockout

-0.72

oun

-0.72

 skelet

-0.72

POSITIVE LOGITS

Indeed

1.53

Asked

1.51

Added

1.39

Others

1.38

Another

1.38

Newsletter

1.37

Despite

1.36

Advertisement

1.35

Refer

1.33

While

1.32

Activations Density 0.270%

terms related to interviews or conversations

instances of strong emotional expressions or sentiments

No Comments

No Known Activations