INDEX

Explanations

phrases related to a specific type of equipment or product, likely related to technology or gaming

oai_token-act-pair · gpt-3.5-turbo

references to combination moves or strategies in games

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

mberg

-0.74

aniel

-0.73

aco

-0.71

oral

-0.69

ady

-0.68

unc

-0.68

 Abraham

-0.66

sburg

-0.65

 Wage

-0.64

 Petty

-0.63

POSITIVE LOGITS

 Breaker

0.91

iques

0.73

 breaker

0.72

 boxes

0.70

ycle

0.70

halla

0.70

 combo

0.70

 between

0.69

-+-+

0.69

 builder

0.68

Activations Density 0.016%

phrases related to a specific type of equipment or product, likely related to technology or gaming

references to combination moves or strategies in games

No Comments

No Known Activations