INDEX

Explanations

phrases involving the word "neither" followed by contrasting elements or situations

oai_token-act-pair · gpt-3.5-turbo

the word "neither," often indicating negation or exclusion in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ournals

-0.83

utterstock

-0.73

egu

-0.70

ahime

-0.68

roxy

-0.67

duc

-0.65

ãĥ¼ãĥ³

-0.65

Bang

-0.64

enos

-0.64

çī

-0.63

POSITIVE LOGITS

nor

0.84

soever

0.77

 side

0.76

theless

0.75

 condone

0.70

_>

0.69

 overtly

0.66

 spouse

0.66

lihood

0.65

 shalt

0.65

Activations Density 0.018%

phrases involving the word "neither" followed by contrasting elements or situations

the word "neither," often indicating negation or exclusion in statements

No Comments

No Known Activations