INDEX

Explanations

the word "robust" or variations of it in different contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "robust" in various contexts, emphasizing strength or effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 dearly

-0.70

Khe

-0.66

ioxide

-0.65

hops

-0.65

 clicked

-0.63

ById

-0.62

OPA

-0.61

 Fever

-0.61

 Jinn

-0.60

frey

-0.60

POSITIVE LOGITS

ly

1.18

ness

1.12

nesses

1.09

ively

0.97

enough

0.94

edly

0.91

 enough

0.90

ament

0.89

mble

0.86

itude

0.86

Activations Density 0.016%

the word "robust" or variations of it in different contexts

occurrences of the term "robust" in various contexts, emphasizing strength or effectiveness

No Comments

No Known Activations