INDEX

Explanations

terms related to weather conditions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Weather" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ioned

-0.88

essors

-0.87

uates

-0.81

essor

-0.80

inates

-0.80

inctions

-0.80

alty

-0.77

acters

-0.77

ificial

-0.74

itable

-0.74

POSITIVE LOGITS

 Powers

0.84

mire

0.75

lings

0.75

hurst

0.75

fell

0.72

bug

0.72

LAN

0.71

burn

0.71

robe

0.70

Bug

0.70

Activations Density 0.021%

terms related to weather conditions

occurrences of the word "Weather" and related terms

No Comments

No Known Activations