INDEX

Explanations

mentions of capabilities or tasks being overstated

oai_token-act-pair · gpt-3.5-turbo

questions related to travel and exploration

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

 msec

-0.68

dyl

-0.67

 aven

-0.64

 elves

-0.63

});

-0.60

 sorce

-0.60

 disg

-0.59

 disarm

-0.59

addons

-0.58

vern

-0.58

POSITIVE LOGITS

 Relationship

1.08

 Away

0.96

 Appro

0.91

 Month

0.91

 Approach

0.91

 Replacement

0.90

 Scale

0.90

 Donation

0.90

 Disorder

0.90

 Therapy

0.90

Activations Density 0.562%

mentions of capabilities or tasks being overstated

questions related to travel and exploration

No Comments

No Known Activations