INDEX

Explanations

comparative phrases and questions

oai_token-act-pair · gpt-3.5-turbo

phrases that express comparisons or highlight differences

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

KO

-0.72

gra

-0.63

hig

-0.61

 poppy

-0.58

POSE

-0.57

staking

-0.57

 simmer

-0.57

oval

-0.57

housing

-0.56

bis

-0.56

POSITIVE LOGITS

?]

1.08

?!

0.98

!?

0.93

0.92

?:

0.92

?),

0.89

?!"

0.86

?)

0.85

?'

0.83

?",

0.83

Activations Density 0.122%

comparative phrases and questions

phrases that express comparisons or highlight differences

No Comments

No Known Activations