INDEX

Explanations

phrases related to lists or series of items

oai_token-act-pair · gpt-3.5-turbo

references to team-related activities and organizations

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

 acet

-0.57

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.55

obil

-0.55

atron

-0.54

parable

-0.53

.''

-0.52

ophobic

-0.51

 caps

-0.48

obar

-0.48

 gland

-0.48

POSITIVE LOGITS

 vying

0.56

 specializing

0.56

 neighb

0.55

ESE

0.55

 themed

0.55

 staffed

0.54

 architectures

0.54

 acad

0.54

 Classics

0.54

 subdiv

0.54

Activations Density 0.995%

phrases related to lists or series of items

references to team-related activities and organizations

No Comments

No Known Activations