INDEX

Explanations

names and terms related to specific products or companies

oai_token-act-pair · gpt-3.5-turbo

sentences or statements punctuated specifically with periods

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

 defe

-0.80

 glim

-0.75

 involuntary

-0.75

 cabbage

-0.75

 induct

-0.75

 unbeat

-0.74

 reception

-0.70

 coil

-0.69

 powering

-0.69

sal

-0.68

POSITIVE LOGITS

Downloadha

1.29

tumblr

1.26

blogspot

1.22

 Whereas

1.17

 However

1.15

 Similarly

1.14

 Conversely

1.13

 Accordingly

1.13

 Likewise

1.12

 Though

1.09

Activations Density 0.840%

names and terms related to specific products or companies

sentences or statements punctuated specifically with periods

No Comments

No Known Activations