INDEX

Explanations

scientific terms and research-related phrases

oai_token-act-pair · gpt-3.5-turbo

scientific or technical descriptions related to experiments or observations

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

aph

-0.39

 detectives

-0.38

Cause

-0.37

itar

-0.37

 depends

-0.36

ritch

-0.36

iaries

-0.36

 sock

-0.36

Story

-0.35

 Rollins

-0.35

POSITIVE LOGITS

åĮ

0.56

 respectively

0.51

]).

0.47

srf

0.44

 dracon

0.43

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.42

çĶ°

0.42

 ç¥ŀ

0.41

anwhile

0.40

äº

0.40

Activations Density 4.650%

scientific terms and research-related phrases

scientific or technical descriptions related to experiments or observations

No Comments

No Known Activations