INDEX

Explanations

verbs related to perception and understanding

oai_token-act-pair · gpt-3.5-turbo

instances of perception or awareness in relation to events or situations

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

phabet

-0.87

osures

-0.78

ankind

-0.74

interstitial

-0.71

sembly

-0.70

aqu

-0.70

afort

-0.68

 wipes

-0.67

iky

-0.66

quer

-0.65

POSITIVE LOGITS

abet

0.74

ledged

0.65

 instinctively

0.63

Pol

0.62

 beforehand

0.62

 themselves

0.61

ctor

0.60

 overhe

0.60

 receptive

0.59

phas

0.59

Activations Density 0.362%

verbs related to perception and understanding

instances of perception or awareness in relation to events or situations

No Comments

No Known Activations