INDEX

Explanations

pronouns and verbs related to actions or decisions

oai_token-act-pair · gpt-3.5-turbo

actions related to helping or supporting others

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

>>>>>>>>

-0.59

................................

-0.58

[/

-0.57

reports

-0.51

++++++++

-0.50

 Explain

-0.50

////////////////////////////////

-0.49

udos

-0.49

++++++++++++++++

-0.49

Nay

-0.49

POSITIVE LOGITS

 supposedly

0.60

 otherwise

0.57

ufact

0.55

 deems

0.54

 deemed

0.53

 inevitably

0.52

 legitimately

0.52

 deem

0.51

udic

0.51

 allegedly

0.50

Activations Density 0.923%

pronouns and verbs related to actions or decisions

actions related to helping or supporting others

No Comments

No Known Activations