INDEX

Explanations

adjective-noun phrases describing divisions or distinctions

oai_token-act-pair · gpt-3.5-turbo

instances of the term "ops" and its variations, likely indicative of errors or issues in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

SHIP

-0.72

 phyl

-0.64

 prisoners

-0.62

 inmates

-0.61

 anesthesia

-0.60

 embodiments

-0.59

 embr

-0.59

theless

-0.59

jad

-0.59

WAYS

-0.56

POSITIVE LOGITS

ops

1.18

heet

0.96

ilon

0.96

yright

0.95

oppers

0.92

imus

0.92

ided

0.90

iate

0.89

olitan

0.87

icle

0.86

Activations Density 0.024%

adjective-noun phrases describing divisions or distinctions

instances of the term "ops" and its variations, likely indicative of errors or issues in communication

No Comments

No Known Activations