INDEX

Explanations

words related to outcomes or consequences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "resulted" indicating outcomes or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

thur

-0.69

 spaced

-0.69

foundation

-0.65

mens

-0.63

 hopping

-0.63

opic

-0.63

nature

-0.61

 Sapp

-0.60

fer

-0.60

fing

-0.59

POSITIVE LOGITS

ĸļ

0.98

swers

0.90

interstitial

0.76

 resulted

0.72

Results

0.70

actionDate

0.70

uments

0.69

UE

0.69

hess

0.69

LOG

0.68

Activations Density 0.018%

words related to outcomes or consequences

occurrences of the word "resulted" indicating outcomes or consequences

No Comments

No Known Activations