INDEX

Explanations

words related to combining or merging things together

oai_token-act-pair · gpt-3.5-turbo

instances of the word "combine" in various contexts

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

den

-0.76

etheless

-0.74

fare

-0.74

estate

-0.71

bis

-0.70

boy

-0.70

writers

-0.69

noon

-0.67

shire

-0.66

kar

-0.66

POSITIVE LOGITS

ãĤ¤ãĥĪ

0.84

 seamlessly

0.83

 dots

0.82

ively

0.76

 sexes

0.76

ibilities

0.74

 genders

0.73

 together

0.73

 combines

0.71

 genres

0.71

Activations Density 0.033%

words related to combining or merging things together

instances of the word "combine" in various contexts

No Comments

No Known Activations