INDEX

Explanations

numerical sequences or codes

oai_token-act-pair · gpt-3.5-turbo

numerical values and metadata related to data, possibly indicating statistics or scores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

omsky

-0.60

vasive

-0.60

usercontent

-0.58

pex

-0.57

 besides

-0.57

Ń·

-0.56

 solvent

-0.55

aird

-0.55

cause

-0.54

 fuss

-0.53

POSITIVE LOGITS

 Awakens

0.69

eca

0.64

0.61

 Mermaid

0.59

onet

0.58

 Metatron

0.56

ciating

0.55

|--

0.55

 Firm

0.54

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.54

Activations Density 0.491%

numerical sequences or codes

numerical values and metadata related to data, possibly indicating statistics or scores

No Comments

No Known Activations