INDEX

Explanations

words related to peaks or high points

oai_token-act-pair · gpt-3.5-turbo

the term "peak" 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 @ 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

icate

-0.77

onsense

-0.74

 Cosponsors

-0.72

signed

-0.70

oured

-0.68

ktop

-0.66

 parted

-0.66

 transpl

-0.66

erie

-0.65

 Mechdragon

-0.63

POSITIVE LOGITS

lite

0.75

imum

0.75

ceed

0.72

 occupancy

0.67

antha

0.66

 peaks

0.65

urb

0.65

lighting

0.64

IER

0.64

waters

0.64

Activations Density 0.029%

words related to peaks or high points

the term "peak" in various contexts

No Comments

No Known Activations