INDEX

Explanations

instances of words related to operations or functioning

oai_token-act-pair · gpt-3.5-turbo

terms related to businesses or entities functioning or conducting operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

grave

-0.75

apest

-0.69

ync

-0.68

ikers

-0.65

ixels

-0.64

 Shards

-0.64

eton

-0.63

alla

-0.62

ildo

-0.62

alon

-0.61

POSITIVE LOGITS

 independently

1.10

 concurrently

0.93

 autonom

0.91

 under

0.87

 efficiently

0.86

 smoothly

0.85

 illegally

0.84

 jointly

0.84

 lawfully

0.83

 within

0.82

Activations Density 0.046%

instances of words related to operations or functioning

terms related to businesses or entities functioning or conducting operations

No Comments

No Known Activations