INDEX

Explanations

phrases related to multiple entities competing or existing in various scenarios

oai_token-act-pair · gpt-3.5-turbo

references to multiple entities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pmwiki

-0.72

activity

-0.64

ople

-0.63

ogle

-0.61

rolog

-0.60

eston

-0.59

vik

-0.59

 EVENTS

-0.57

taboola

-0.57

ertain

-0.56

POSITIVE LOGITS

 apiece

1.50

 totaling

1.25

 vying

1.09

 simultaneously

1.08

 respectively

1.06

 consecut

1.04

 concurrently

0.96

viz

0.95

 separated

0.93

 together

0.92

Activations Density 0.355%

phrases related to multiple entities competing or existing in various scenarios

references to multiple entities or groups

No Comments

No Known Activations