INDEX

Explanations

instances of the word 'any' followed by a word that completes a specific phrase or concept

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "any" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

gypt

-0.80

romy

-0.72

 Originally

-0.70

raid

-0.70

expensive

-0.67

rex

-0.67

ovy

-0.66

iesta

-0.66

 alot

-0.65

arettes

-0.64

POSITIVE LOGITS

 semblance

1.20

 attempt

1.02

 resemblance

1.00

 deviation

0.98

 conceivable

0.96

body

0.94

THING

0.94

 deviations

0.92

 future

0.91

how

0.90

Activations Density 0.068%

instances of the word 'any' followed by a word that completes a specific phrase or concept

occurrences of the word "any" in various contexts

No Comments

No Known Activations