INDEX

Explanations

phrases expressing understanding or disagreement

oai_token-act-pair · gpt-3.5-turbo

expressions of doubt or uncertainty

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

ortment

-0.70

 unavoid

-0.62

 unsus

-0.62

 overcoming

-0.61

 respectively

-0.61

vironment

-0.61

BIL

-0.61

atars

-0.59

 awaited

-0.58

 overcome

-0.58

POSITIVE LOGITS

 anymore

1.04

 myself

0.97

yet

0.85

nor

0.80

poke

0.78

 anybody

0.72

 EVER

0.71

à¼

0.69

 specifics

0.67

 anywhere

0.63

Activations Density 0.293%

phrases expressing understanding or disagreement

expressions of doubt or uncertainty

No Comments

No Known Activations