INDEX

Explanations

phrases related to interpersonal interactions and physical actions

oai_token-act-pair · gpt-3.5-turbo

interactions filled with emotional weight and social dynamics

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

osate

-0.86

displayText

-0.79

 Berman

-0.78

busters

-0.77

SPONSORED

-0.75

Downloadha

-0.74

!'"

-0.74

govtrack

-0.73

Critics

-0.71

,'"

-0.70

POSITIVE LOGITS

 Jaune

1.04

 Weasley

0.96

 Pyrrha

0.93

 grin

0.92

 shudder

0.87

blance

0.85

 nodded

0.84

 soothing

0.84

 sighed

0.83

 faint

0.82

Activations Density 0.670%

phrases related to interpersonal interactions and physical actions

interactions filled with emotional weight and social dynamics

No Comments

No Known Activations