INDEX

Explanations

comparative adjectives related to improvement or preference

oai_token-act-pair · gpt-3.5-turbo

comparisons emphasizing the concept of "better."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gemony

-0.70

alion

-0.65

iasm

-0.64

 Roche

-0.61

pex

-0.61

ggle

-0.61

how

-0.61

regate

-0.60

mberg

-0.60

RF

-0.58

POSITIVE LOGITS

 suited

1.16

 than

1.03

 behaved

0.89

luaj

0.76

 smelling

0.74

served

0.72

 insulated

0.72

than

0.72

 tasting

0.71

 acquainted

0.71

Activations Density 0.086%

comparative adjectives related to improvement or preference

comparisons emphasizing the concept of "better."

No Comments

No Known Activations