INDEX

Explanations

terms related to knowledge and expertise

oai_token-act-pair · gpt-3.5-turbo

references to knowledge and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ishable

-0.63

issions

-0.63

etheus

-0.62

redd

-0.62

atos

-0.60

 Predator

-0.60

 Devils

-0.60

 earthqu

-0.58

itter

-0.58

odd

-0.58

POSITIVE LOGITS

ledge

1.19

lege

1.19

 glean

0.92

fulness

0.90

reading

0.86

 comprehension

0.85

ledged

0.85

lessness

0.77

 knowledge

0.75

liness

0.74

Activations Density 0.040%

terms related to knowledge and expertise

references to knowledge and understanding

No Comments

No Known Activations