INDEX

Explanations

comparisons using the word "like"

oai_token-act-pair · gpt-3.5-turbo

metaphors and comparisons in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ason

-0.71

 Ezek

-0.70

everal

-0.69

ename

-0.66

elfth

-0.66

rade

-0.65

rue

-0.65

mber

-0.65

aven

-0.63

oubted

-0.63

POSITIVE LOGITS

 except

0.99

 minus

0.84

 Except

0.84

 wherein

0.79

minus

0.74

 albeit

0.74

 whereby

0.71

 insofar

0.69

 kinda

0.66

ombies

0.65

Activations Density 0.464%

comparisons using the word "like"

metaphors and comparisons in descriptions

No Comments

No Known Activations